© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3365
    Prev
    Next
    INDEX
    Explanations

    uses of the word or concept of "seeing"

    oai_token-act-pair · gemini-2.0-flash

    see

    np_max-act-logits · gemini-2.0-flash

    see Method used: 1 — because all max-activating tokens are "see"/"seen"/"seeing"/"saw"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    новниш
    -0.77
     doubtnut
    -0.76
     snippetHide
    -0.73
    principalColumn
    -0.73
     contextLoads
    -0.73
     tartalomajánló
    -0.72
    ніципалі
    -0.70
     Britann
    -0.68
     itſelf
    -0.68
     ―――――
    -0.67
    POSITIVE LOGITS
     "/";
    0.53
    leid
    0.49
     what
    0.49
    와
    0.46
     me
    0.45
     grava
    0.44
     my
    0.44
     &
    0.44
     an
    0.43
    Hidden
    0.43
    Activations Density 7.188%

    No Known Activations