© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3542
    Prev
    Next
    INDEX
    Explanations

    intent structure

    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_5_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
    દ્ધ
    0.65
    টাল
    0.64
    ট
    0.60
    ached
    0.59
     большой
    0.59
    jaro
    0.58
    liness
    0.57
    achievement
    0.57
    ‍♀️
    0.56
    чих
    0.56
    POSITIVE LOGITS
    choline
    0.67
     Toutefois
    0.67
     Định
    0.67
    ुस्तान
    0.66
     Prendre
    0.66
    <unused368>
    0.65
    ℉
    0.64
    тил
    0.64
    деги
    0.64
    ᐉ
    0.64
    Activations Density 0.011%

    No Known Activations