© 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. 11336
    Prev
    Next
    INDEX
    Explanations

    text about politics or political issues.

    oai_token-act-pair · 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
    TagMode
    -0.73
    WebElementEntity
    -0.71
    LookAnd
    -0.71
    ToFit
    -0.65
     /\.
    -0.65
     }{@
    -0.63
    帖最后由
    -0.63
    GroupLayout
    -0.62
    例句
    -0.61
     snippetHide
    -0.56
    POSITIVE LOGITS
    ftagPool
    0.55
     estekak
    0.50
    IsMutable
    0.48
     rayures
    0.45
    urilor
    0.45
    taban
    0.45
    rigkeit
    0.45
    IGI
    0.44
     gynnwys
    0.43
    Ос
    0.43
    Activations Density 10.538%

    No Known Activations