© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    personal pronouns used in questions

    oai_token-act-pair · gemini-2.0-flash

    say "can"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    interopRequire
    -0.82
     himſelf
    -0.77
     myſelf
    -0.75
    parsedMessage
    -0.73
    Tembelea
    -0.73
    nextProps
    -0.71
    EndInit
    -0.69
    ⓧ
    -0.69
     surla
    -0.69
    InjectAttribute
    -0.69
    POSITIVE LOGITS
     can
    2.95
    can
    2.30
    Can
    2.08
     Can
    2.06
     could
    1.80
     kann
    1.66
     können
    1.62
     CAN
    1.62
     bisa
    1.52
     dapat
    1.46
    Activations Density 1.485%

    No Known Activations