© 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. 63287
    Prev
    Next
    INDEX
    Explanations

    what questions

    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
     是
    0.66
     that
    0.63
     adalah
    0.63
    คือ
    0.63
    是大
    0.61
     là
    0.59
    that
    0.59
    是
    0.57
     هو
    0.56
     คือ
    0.56
    POSITIVE LOGITS
     Vo
    0.84
    Vo
    0.77
     vo
    0.73
     voila
    0.73
     Voilà
    0.72
     Viola
    0.68
    Voilà
    0.64
    vo
    0.64
     VO
    0.64
     voilà
    0.64
    Activations Density 0.030%

    No Known Activations