© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12501
    Prev
    Next
    INDEX
    Explanations

    things that are liked, preferred, or enjoyed

    oai_token-act-pair · gemini-2.0-flash

    favorite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    setVerticalGroup
    -0.83
     nahilalakip
    -0.82
    providedIn
    -0.68
    fromnode
    -0.66
    UnusedPrivate
    -0.63
    ViewFeatures
    -0.62
     estekak
    -0.60
    IndentedString
    -0.60
    SerializedSize
    -0.60
    bootstrapcdn
    -0.60
    POSITIVE LOGITS
     breeds
    0.51
    leun
    0.49
    ophilia
    0.48
     reserves
    0.46
    Matchers
    0.46
    icycle
    0.46
     Beatles
    0.46
    sendRedirect
    0.45
    ontes
    0.45
     names
    0.45
    Activations Density 3.357%

    No Known Activations