© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15270
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    aligned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Paglinawan
    -0.90
    endphp
    -0.78
    ViewImports
    -0.73
    +#+#
    -0.73
     мәкал
    -0.70
     <<<<<<<<<<<<<<
    -0.69
     betweenstory
    -0.66
    parsedMessage
    -0.65
    niająca
    -0.65
     estekak
    -0.65
    POSITIVE LOGITS
    RenderAtEndOf
    0.41
    abra
    0.39
     Schu
    0.35
    </em>
    0.35
    nom
    0.35
    vers
    0.34
    強
    0.33
     сво
    0.33
    hoga
    0.33
    KOK
    0.32
    Activations Density 1.541%

    No Known Activations