© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9435
    Prev
    Next
    INDEX
    Explanations

    references to specific months, years, and legal appeals

    oai_token-act-pair · gemini-2.0-flash

    dates and time references

    np_token-act-pair-logits · gpt-4o-mini

    Dates and years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    [];
    -0.57
    ;
    -0.52
    ('');
    -0.51
    !
    -0.51
    __).
    -0.49
    ();
    -0.48
     which
    -0.47
    ("");
    -0.46
     '';
    -0.46
    oli
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.93
    migrationBuilder
    0.83
    AndEndTag
    0.82
    featureID
    0.79
    IntoConstraints
    0.78
    
    0.78
    StructEnd
    0.77
     numberOfRows
    0.76
     myſelf
    0.75
     تضيفلها
    0.73
    Activations Density 1.618%

    No Known Activations