© 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. 5448
    Prev
    Next
    INDEX
    Explanations

    markers of opinion, reasoning, and questions, especially involving "you", "could", "would", and "anyone".

    oai_token-act-pair · gemini-2.0-flash

    Expressing opinions or disbelief

    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
    migrationBuilder
    -0.75
    okości
    -0.71
    Viited
    -0.66
     JSTOR
    -0.63
    richTextPanel
    -0.57
    styleType
    -0.56
    Izvori
    -0.55
     JpaRepository
    -0.53
     Anexo
    -0.52
    pointments
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.69
    ⓧ
    0.52
    uxxxx
    0.52
    cookieParser
    0.48
    tagHelperRunner
    0.47
     Popis
    0.47
    cstring
    0.46
     发表于
    0.45
     giáp
    0.45
    حياته
    0.45
    Activations Density 14.567%

    No Known Activations