© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of concern or strong opinions about something

    oai_token-act-pair · gemini-2.0-flash

    cares, figs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Roskov
    -0.68
    getMenuInflater
    -0.56
    styleType
    -0.56
    GraphicsUnit
    -0.55
     فريبيس
    -0.51
    SharedDtor
    -0.49
    uitable
    -0.47
     Hah
    -0.47
    ,:),
    -0.46
     Acme
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.68
    cares
    0.65
     indifference
    0.65
     mattered
    0.64
    IntoConstraints
    0.63
     peduli
    0.63
    ksikon
    0.62
     indifer
    0.60
     matter
    0.58
     cares
    0.58
    Activations Density 2.156%

    No Known Activations