© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    vaar
    -0.50
    anna
    -0.50
    ueras
    -0.46
    äk
    -0.44
    illa
    -0.44
     Carrington
    -0.43
    usk
    -0.43
    ood
    -0.43
    Enqueue
    -0.42
    <bos>
    -0.42
    POSITIVE LOGITS
    expandindo
    0.59
    migrationBuilder
    0.59
    Diwedd
    0.58
    MLLoader
    0.52
     kasarigan
    0.52
    ViewImports
    0.52
     disambiguazione
    0.48
     فريبيس
    0.48
     MonoBehaviour
    0.48
    //
    0.47
    Activations Density 0.168%

    No Known Activations