© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 772
    Prev
    Next
    INDEX
    Explanations

    location, place, or time references.

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LookAnd
    -0.67
    WebVitals
    -0.66
    expandindo
    -0.60
     мәкал
    -0.60
    例句
    -0.59
    jsxFileName
    -0.57
    SwitchCompat
    -0.57
    exitRule
    -0.57
    ForResult
    -0.56
     Signalez
    -0.55
    POSITIVE LOGITS
     over
    3.39
    over
    2.56
    Over
    2.52
     Over
    2.48
     OVER
    2.25
     över
    1.99
    OVER
    1.88
     über
    1.73
     над
    1.53
    overs
    1.52
    Activations Density 2.025%

    No Known Activations