© 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. 229165
    Prev
    Next
    INDEX
    Explanations

    xx

    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
     μορ
    0.41
    ោង
    0.39
     działa
    0.38
     ഉപ
    0.37
     هدف
    0.37
    狠
    0.36
    INGO
    0.35
    ücher
    0.34
     ವಿಶ
    0.34
    まった
    0.34
    POSITIVE LOGITS
    Ou
    0.55
     ou
    0.55
     Ou
    0.54
     або
    0.50
    斫
    0.43
     Button
    0.41
     Riggs
    0.40
     او
    0.40
     OU
    0.39
     oder
    0.39
    Activations Density 0.000%

    No Known Activations