© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261342
    Prev
    Next
    INDEX
    Explanations

    itch, hit, Hitchcock

    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_5_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
    ו
    1.31
    1
    1.21
    the
    1.14
    on
    1.13
    ul
    1.12
    ن
    1.07
    an
    1.06
    ar
    1.05
     zahlen
    1.04
    ן
    1.04
    POSITIVE LOGITS
     I
    1.41
    나
    1.28
    ۰
    1.22
    یت
    1.15
    ä
    1.09
     fabricación
    1.02
    ک
    1.00
    行う
    0.98
    ५
    0.98
    지가
    0.96
    Activations Density 0.000%

    No Known Activations