© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9053
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     சது
    0.70
     yksi
    0.67
    AT
    0.66
     pula
    0.65
     تمہ
    0.62
    叵
    0.62
     geliş
    0.62
     talaga
    0.61
     въ
    0.59
     തി
    0.58
    POSITIVE LOGITS
     pronotum
    0.75
     STEELS
    0.74
    鸵
    0.74
     unpre
    0.73
     Великобритании
    0.72
     Heathrow
    0.70
     Steele
    0.68
    ően
    0.67
    唑
    0.66
    FFER
    0.66
    Activations Density 0.001%

    No Known Activations