© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228846
    Prev
    Next
    INDEX
    Explanations

    tech and places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ｝
    0.42
    <0x9A>
    0.40
     치
    0.38
     fle
    0.36
     indir
    0.36
    uit
    0.35
     Петра
    0.35
     Acc
    0.35
     Ai
    0.35
     Помимо
    0.35
    POSITIVE LOGITS
    MPa
    0.42
    emf
    0.38
    immä
    0.37
     Korea
    0.36
     atent
    0.35
    ㄾ
    0.35
     Tons
    0.34
     dads
    0.34
    ogie
    0.34
    auch
    0.34
    Activations Density 0.000%

    No Known Activations