© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3918
    Prev
    Next
    INDEX
    Explanations

    references to the Murrinh-Patha language and the area where it is spoken

    oai_token-act-pair · gemini-2.0-flash

    Australian topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <bos>
    -0.40
    paksa
    -0.39
    jupiter
    -0.39
    Nguyễn
    -0.38
     taglia
    -0.38
     de
    -0.37
     voorkomen
    -0.37
     Nguyễn
    -0.37
    obiettivo
    -0.36
    enggarakan
    -0.36
    POSITIVE LOGITS
    parsedMessage
    1.03
    featureID
    1.02
     архивлан
    0.82
    aarrggbb
    0.80
    errHandler
    0.79
    ResumeLayout
    0.73
     autorytatywna
    0.71
    AddTagHelper
    0.70
     дописавши
    0.69
    expandindo
    0.69
    Activations Density 1.089%

    No Known Activations