© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130577
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    address
    0.25
    list
    0.22
    label
    0.22
    int
    0.21
    select
    0.21
     u
    0.20
    node
    0.20
    than
    0.20
      
    0.20
    re
    0.20
    POSITIVE LOGITS
    瑢
    0.22
     امنیت
    0.19
     modalCard
    0.19
    锗
    0.19
    珲
    0.18
     ಮನೆ
    0.18
    軍
    0.18
     currentGame
    0.18
     Япо
    0.18
     berkom
    0.18
    Activations Density 0.000%

    No Known Activations