© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63433
    Prev
    Next
    INDEX
    Explanations

    lookingseesextendsout

    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_41_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
     out
    2.28
     Out
    1.56
    Out
    1.53
     из
    1.45
    out
    1.38
     OUT
    1.34
    出
    1.34
     outta
    1.30
    ออก
    1.25
     आउट
    1.22
    POSITIVE LOGITS
    endu
    0.39
    pounds
    0.38
    vertine
    0.38
    ender
    0.38
    September
    0.37
    ッチ
    0.36
    ແ
    0.36
     Ender
    0.36
    மர்
    0.34
     endian
    0.34
    Activations Density 0.021%

    No Known Activations