© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6638
    Prev
    Next
    INDEX
    Explanations

    words relating to death and crime investigations

    oai_token-act-pair · gemini-2.0-flash

    death, discovery, bad situation

    np_max-act-logits · gemini-2.0-flash

    say "death" words Method used: 2 — because following tokens frequently denote death or hanging — say "death" words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.84
    MessageTagHelper
    -0.76
    MENAFN
    -0.68
    resents
    -0.68
     Efq
    -0.66
    WebElementEntity
    -0.66
    énario
    -0.65
    Климат
    -0.65
    cipal
    -0.64
    hematical
    -0.63
    POSITIVE LOGITS
     ready
    0.50
     with
    0.49
     surrounded
    0.48
     running
    0.48
     operating
    0.47
     nakalista
    0.46
    Билгалдахарш
    0.45
     buried
    0.45
     in
    0.44
     locked
    0.43
    Activations Density 1.626%

    No Known Activations