© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9414
    Prev
    Next
    INDEX
    Explanations

    specific comment delimiters used in code

    oai_token-act-pair · gemini-2.0-flash

    asterisk symbol

    np_max-act · gemini-2.0-flash
    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
     myſelf
    -1.95
     itſelf
    -1.94
     pleaſure
    -1.79
     Monfieur
    -1.77
     Efq
    -1.76
     Theſe
    -1.76
     fubject
    -1.67
     Majefty
    -1.67
     ſtate
    -1.63
     raiſ
    -1.63
    POSITIVE LOGITS
    .
    1.09
    <eos>
    0.90
    //
    0.89
    /
    0.81
     a
    0.81
     J
    0.80
    }
    0.79
     M
    0.79
    ///
    0.77
    M
    0.77
    Activations Density 0.129%

    No Known Activations