© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    mentions of names, whether individuals, nicknames, or species names

    oai_token-act-pair · gemini-2.0-flash

    say name

    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
     called
    -1.63
    called
    -1.43
     Called
    -1.40
     CALLED
    -1.36
    Called
    -1.34
     titled
    -1.23
     llamado
    -1.19
     termed
    -1.15
     llamada
    -1.13
     называется
    -1.13
    POSITIVE LOGITS
    :+:
    0.69
    saraba
    0.58
     ویکی‌پدیای
    0.57
     CGSize
    0.56
    INCREF
    0.56
    ंदीखरीदारी
    0.55
    MigrationBuilder
    0.54
    idom
    0.53
    ///</
    0.52
    
    0.52
    Activations Density 1.426%

    No Known Activations