© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12802
    Prev
    Next
    INDEX
    Explanations

    mentions of primary importance or reasons

    oai_token-act-pair · gemini-2.0-flash

    main/primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.83
    bewerken
    -0.81
    AndEndTag
    -0.79
    Rohy
    -0.78
    GEBURTSDATUM
    -0.77
     /\.(
    -0.76
    TestingModule
    -0.75
     Roskov
    -0.74
    MigrationBuilder
    -0.72
    ConstraintMaker
    -0.72
    POSITIVE LOGITS
     We
    0.42
    marck
    0.42
     mergeFrom
    0.42
     He
    0.41
     Inch
    0.40
     inch
    0.39
    getWriter
    0.39
     M
    0.38
     gammal
    0.38
     B
    0.38
    Activations Density 1.568%

    No Known Activations