© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially the name "Mary"

    oai_token-act-pair · gemini-2.0-flash

    Mary/Marie

    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
     ModelExpression
    -0.80
    InjectAttribute
    -0.76
    MigrationBuilder
    -0.75
    ніципа
    -0.73
     Paglinawan
    -0.71
    ThroughAttribute
    -0.69
    DeleteBehavior
    -0.69
     estekak
    -0.69
     שוליים
    -0.64
    AsUp
    -0.63
    POSITIVE LOGITS
    ществ
    0.44
     flèche
    0.43
    هم
    0.42
    setAge
    0.42
    بخش
    0.41
    valu
    0.40
     بخش
    0.40
    CN
    0.40
     adaptación
    0.39
     aprovechar
    0.39
    Activations Density 0.368%

    No Known Activations