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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1526
    Prev
    Next
    INDEX
    Explanations

    passages that describe a hunting tool used by a hunter to hunt and bring down prey.

    oai_token-act-pair · gemini-2.0-flash

    video games and game design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     game
    -3.02
     Game
    -2.77
    game
    -2.75
    Game
    -2.72
     GAME
    -2.61
     games
    -2.55
     Games
    -2.47
    GAME
    -2.39
    Games
    -2.34
    games
    -2.33
    POSITIVE LOGITS
    PerformLayout
    0.77
    AnchorStyles
    0.57
    TextWatcher
    0.55
    IntoConstraints
    0.48
    참고
    0.47
    mybatisplus
    0.45
    stringValue
    0.45
    UnknownFields
    0.45
    Aholisi
    0.45
    chenkt
    0.44
    Activations Density 1.317%

    No Known Activations