© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9468
    Prev
    Next
    INDEX
    Explanations

    words or phrases ending in "tion" or "ment" or related to legal contexts.

    oai_token-act-pair · gemini-2.0-flash

    legal/official jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ing
    -0.64
    ulate
    -0.57
    ibrate
    -0.53
    genstein
    -0.50
    ING
    -0.46
    itulo
    -0.46
    ]<<"
    -0.45
    INTAIN
    -0.45
    Executor
    -0.43
    chner
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.88
     uska
    0.76
    IsContent
    0.73
     surla
    0.73
     XCTest
    0.72
     imposition
    0.70
     pinulongan
    0.70
     ModelExpression
    0.69
    CloseOperation
    0.66
     resourceCulture
    0.66
    Activations Density 2.631%

    No Known Activations