© 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. 121669
    Prev
    Next
    INDEX
    Explanations

    IT professionals

    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
    Negative Logits
    in
    0.98
    inizi
    0.89
    し
    0.79
    ার
    0.69
    er
    0.68
    ر
    0.68
    t
    0.67
    arında
    0.67
    ar
    0.66
    োজনে
    0.65
    POSITIVE LOGITS
    ة
    0.86
    س
    0.86
    نه
    0.83
    ü
    0.83
    }$
    0.78
    }$,
    0.78
    يت
    0.77
    า
    0.76
    *
    0.71
     externa
    0.68
    Activations Density 0.002%

    No Known Activations