© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6170
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating disagreement, legal/scientific challenges, warnings, or statistical oddities

    oai_token-act-pair · gemini-2.0-flash

    over

    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
    expandindo
    -0.69
    LookAnd
    -0.69
    WebVitals
    -0.65
    脚注の使い方
    -0.63
    contentLoaded
    -0.59
     typelib
    -0.58
    GIVEREF
    -0.57
    IContainer
    -0.57
    Diweddarwch
    -0.57
    ///</
    -0.56
    POSITIVE LOGITS
     over
    3.72
    over
    3.03
    Over
    2.89
     Over
    2.84
     OVER
    2.61
    OVER
    2.30
     över
    2.25
    overs
    1.99
     über
    1.97
    オーバー
    1.81
    Activations Density 11.472%

    No Known Activations