© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12879
    Prev
    Next
    INDEX
    Explanations

    physics and mathematics notation

    oai_token-act-pair · gemini-2.0-flash

    eigenvalues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ">//
    -0.69
    tagHelperRunner
    -0.67
     Efq
    -0.66
     himſelf
    -0.66
     ModelExpression
    -0.65
    цездатний
    -0.64
     perfons
    -0.63
    HtmlAttribute
    -0.63
     Majefty
    -0.63
    ulism
    -0.62
    POSITIVE LOGITS
    SaveChangesAsync
    0.59
     susi
    0.53
    ContentValues
    0.48
    ciu
    0.46
     Dickson
    0.44
    eiro
    0.44
    mpel
    0.43
    ้อง
    0.43
    dica
    0.43
    гда
    0.42
    Activations Density 5.171%

    No Known Activations