© 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. 10460
    Prev
    Next
    INDEX
    Explanations

    statements of fact or proven results

    oai_token-act-pair · gemini-2.0-flash

    descriptions and properties

    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
     الحره
    -0.62
     in
    -0.58
     the
    -0.56
     un
    -0.52
     I
    -0.50
     an
    -0.50
    ,
    -0.49
     most
    -0.48
    getContentPane
    -0.46
     some
    -0.46
    POSITIVE LOGITS
    :✨
    0.95
    ]--;
    0.94
     $_"
    0.83
     Anſ
    0.78
     ſch
    0.74
     iſt
    0.73
     Efq
    0.72
     Theſe
    0.71
     Beſ
    0.71
     endforeach
    0.69
    Activations Density 3.157%

    No Known Activations