© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3072
    Prev
    Next
    INDEX
    Explanations

    code snippets and related punctuation and quotation marks

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    Negative Logits
     Efq
    -1.10
    ^(@)
    -0.93
     itſelf
    -0.91
     doubtnut
    -0.84
    NUMX
    -0.79
     myſelf
    -0.79
     $_"
    -0.77
     himſelf
    -0.75
     Monfieur
    -0.74
    moiselle
    -0.72
    POSITIVE LOGITS
    ());
    1.08
    ){
    1.05
    ())
    0.99
     );
    0.97
    ()).
    0.95
    );//
    0.95
    (),
    0.93
    ());//
    0.93
    );
    0.91
     })
    0.91
    Activations Density 3.050%

    No Known Activations