© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    descriptions of a woman shoplifting.

    oai_token-act-pair · gemini-2.0-flash

    female

    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
    Negative Logits
    MigrationBuilder
    -1.17
     betweenstory
    -1.13
     NSCoder
    -1.09
     ModelExpression
    -1.07
    TypedDataSet
    -1.05
    saraba
    -1.02
     Exactos
    -0.99
     JpaRepository
    -0.96
    StoryboardSegue
    -0.96
    ьаж
    -0.94
    POSITIVE LOGITS
     female
    0.62
    female
    0.50
     male
    0.50
     
    0.48
    Female
    0.48
    女性の
    0.48
     FEMALE
    0.47
     Female
    0.47
    inalis
    0.43
     range
    0.42
    Activations Density 3.921%

    No Known Activations