© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10842
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming code snippets

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash

    "▁-" Method used: 1 — because MAX_ACTIVATING_TOKENS are identical ("▁-") — ▁-

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -2.17
     in
    -1.73
     (
    -1.66
     and
    -1.63
    .
    -1.59
     
    -1.57
     a
    -1.49
     the
    -1.40
     for
    -1.37
     as
    -1.37
    POSITIVE LOGITS
     Monfieur
    3.55
     myſelf
    3.28
     Efq
    3.27
     Theſe
    3.17
     itſelf
    3.11
     Anſ
    3.05
     Reſ
    3.00
     Diſ
    2.98
     Jefus
    2.94
     Majefty
    2.88
    Activations Density 7.259%

    No Known Activations