© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5152
    Prev
    Next
    INDEX
    Explanations

    gestures, key presses, events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    us
    2.43
    ون
    2.34
    ع
    2.09
    ट
    2.05
    و
    2.04
     ruta
    2.02
    as
    2.02
    tive
    1.99
    ется
    1.97
    sche
    1.97
    POSITIVE LOGITS
     supersymmetry
    2.23
    掍
    2.18
    ଼
    2.04
    injury
    2.01
     hyperglycemia
    1.99
     torsional
    1.98
     acupuncture
    1.97
     unbelievable
    1.97
     landmarks
    1.93
     Injury
    1.93
    Activations Density 0.090%

    No Known Activations