© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    text discussing soccer positions and players

    oai_token-act-pair · gemini-2.0-flash

    back

    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
    kapp
    -0.49
    стви
    -0.48
    føl
    -0.47
    standing
    -0.47
     dàng
    -0.46
     hombro
    -0.45
    tigo
    -0.44
     stund
    -0.43
    facing
    -0.43
    häng
    -0.42
    POSITIVE LOGITS
    دانشنامهٔ
    0.72
    ConstraintMaker
    0.68
     समीक्षाओं
    0.66
    IsContent
    0.66
    évaluateur
    0.63
    AnimationsModule
    0.63
    MessageOf
    0.62
    IUrlHelper
    0.62
    ThroughAttribute
    0.61
    zzleHttp
    0.61
    Activations Density 0.343%

    No Known Activations