© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33580
    Prev
    Next
    INDEX
    Explanations

    vital **importance**, **functions**

    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_3_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
    0.81
    ne
    0.74
    ب
    0.68
    ität
    0.67
    ll
    0.66
    नी
    0.66
     उम्मीदवार
    0.65
    ОВ
    0.64
     instituições
    0.64
    తో
    0.63
    POSITIVE LOGITS
    ри
    0.93
    e
    0.87
    ir
    0.83
    i
    0.79
    ية
    0.78
    ে
    0.73
    ia
    0.72
    ור
    0.71
    arı
    0.69
    after
    0.69
    Activations Density 0.014%

    No Known Activations