© 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. 228718
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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
    sever
    0.44
    res
    0.42
    legend
    0.41
    reg
    0.41
    police
    0.41
    respect
    0.41
    resident
    0.40
    <em>
    0.40
    rel
    0.40
    star
    0.40
    POSITIVE LOGITS
     Af
    0.43
    曌
    0.40
     mati
    0.40
    opencamera
    0.40
     Bxc
    0.40
     Akan
    0.40
     Astrology
    0.40
     ಕಾಲ
    0.40
     ГӀ
    0.40
    呋
    0.39
    Activations Density 0.001%

    No Known Activations