© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4796
    Prev
    Next
    INDEX
    Explanations

    HTML table elements, especially table headers, table rows, and table data cells

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    starch
    -0.69
    󠁮
    -0.63
    bead
    -0.61
    vantages
    -0.61
    pecies
    -0.60
     مشين
    -0.60
    vamente
    -0.59
    intenance
    -0.58
     vnd
    -0.57
     Starch
    -0.57
    POSITIVE LOGITS
    PreAuthorize
    0.49
     $
    0.46
    CloseOperation
    0.44
     onCancelled
    0.44
     autorytatywna
    0.44
    XmlType
    0.43
    ChildScrollView
    0.43
    arResult
    0.43
    HandlerContext
    0.43
    EndContext
    0.41
    Activations Density 0.292%

    No Known Activations