© 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. 3671
    Prev
    Next
    INDEX
    Explanations

    distress

    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
    <unused42>
    1.21
    ཌ
    1.14
     chargingStation
    1.14
    нды
    1.13
    缁
    1.12
    存在する
    1.12
    ﺱ
    1.06
     temu
    1.05
     защиты
    1.05
     earning
    1.05
    POSITIVE LOGITS
    c
    1.08
    ка
    1.03
    or
    1.01
    kannya
    0.95
    е
    0.94
    der
    0.93
    kers
    0.90
    部
    0.88
     मचा
    0.88
    onium
    0.86
    Activations Density 0.015%

    No Known Activations