© 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. 7165
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conflict, negative events, and historical accounts.

    oai_token-act-pair · gemini-2.0-flash

    described/mentioned

    np_max-act-logits · gemini-2.0-flash
    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
     EdgeInsets
    -0.55
    ruptedException
    -0.54
    lapsingToolbar
    -0.52
    outer
    -0.47
    dbh
    -0.47
    ây
    -0.46
    ABN
    -0.45
     wzgl
    -0.45
    roglo
    -0.45
    PyExc
    -0.44
    POSITIVE LOGITS
     mentioned
    1.34
     described
    1.28
     depicted
    1.24
     listed
    1.20
    mentioned
    1.15
     Mentioned
    1.11
     portrayed
    1.10
     Described
    1.09
     discussed
    1.09
    described
    1.08
    Activations Density 3.858%

    No Known Activations