© 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. 8144
    Prev
    Next
    INDEX
    Explanations

    language having to do with international cooperation on terrorism

    oai_token-act-pair · gemini-2.0-flash

    World events and politics

    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
    RenderAtEndOf
    -0.88
    rungsseite
    -0.81
    makeText
    -0.75
     Chwiliwch
    -0.72
    IsContent
    -0.72
    CloseOperation
    -0.69
     дописавши
    -0.68
    verwijspagina
    -0.66
    contentLoaded
    -0.63
    parsedMessage
    -0.63
    POSITIVE LOGITS
    WireFormatLite
    0.53
    endsection
    0.52
    Читати
    0.52
     FAST
    0.51
    AndEndTag
    0.48
    ỡ
    0.47
    huahua
    0.46
    Види
    0.45
     comigo
    0.44
    volve
    0.43
    Activations Density 6.536%

    No Known Activations