© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2241
    Prev
    Next
    INDEX
    Explanations

    the end of the document

    oai_token-act-pair · gemini-2.0-flash

    Finally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ujednoznacz
    -0.58
     trained
    -0.57
    <bos>
    -0.55
    RenderAtEndOf
    -0.53
    BeginContext
    -0.53
     kasarigan
    -0.52
    trained
    -0.51
    Становништво
    -0.49
    Климат
    -0.47
    ArgsConstructor
    -0.47
    POSITIVE LOGITS
    kloped
    0.73
    QMetaType
    0.67
     Houſe
    0.60
    .³
    0.60
     avoient
    0.59
    แน่น
    0.58
    saraba
    0.58
     BorderSide
    0.57
     مرئيه
    0.57
    ValueGeneration
    0.54
    Activations Density 5.555%

    No Known Activations