© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167176
    Prev
    Next
    INDEX
    Explanations

    news

    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_56_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
    seven
    0.43
    US
    0.41
    upam
    0.40
    run
    0.39
    <0xB3>
    0.38
    cuenta
    0.38
     bảy
    0.37
    ۷
    0.37
    ⑦
    0.37
     كوم
    0.36
    POSITIVE LOGITS
     ment
    0.45
     feel
    0.44
     leftmost
    0.44
     Knut
    0.42
     ments
    0.42
     booklets
    0.42
    ментів
    0.41
     Crook
    0.40
     sexist
    0.39
     partially
    0.39
    Activations Density 0.000%

    No Known Activations