Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6871
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to burden, stress, requirements, or demands

    oai_token-act-pair · gemini-2.0-flash

    burdens, constraints, pressure

    np_max-act-logits · gemini-2.0-flash
    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
    KommentareTeilen
    -0.68
    principalColumn
    -0.65
     يتيمه
    -0.60
     endwhile
    -0.60
    UnsafeEnabled
    -0.56
     numberWith
    -0.56
    dataIndex
    -0.55
    numerusform
    -0.53
    stylesheet
    -0.52
     onAnimation
    -0.52
    POSITIVE LOGITS
     placed
    0.56
    jooq
    0.55
     Placed
    0.54
    RegressionTest
    0.52
     particuliers
    0.51
    WireFormat
    0.48
     put
    0.48
     contraintes
    0.46
     bénévoles
    0.45
    impose
    0.44
    Activations Density 1.205%

    No Known Activations