© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11233
    Prev
    Next
    INDEX
    Explanations

    references to people and themselves

    oai_token-act-pair · gemini-2.0-flash

    himself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     varios
    -0.56
     several
    -0.56
     successively
    -0.55
     diverses
    -0.54
     previously
    -0.54
     muligt
    -0.54
     various
    -0.53
     
    -0.52
     Several
    -0.52
     himself
    -0.51
    POSITIVE LOGITS
     nahilalakip
    0.90
    AccessorTable
    0.81
     Мексичка
    0.79
    MigrationBuilder
    0.78
     StatefulWidget
    0.77
    liothèque
    0.76
    LookAnd
    0.76
     ProtoMessage
    0.76
    Cyfeiriadau
    0.74
     تضيفلها
    0.74
    Activations Density 1.259%

    No Known Activations