© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200370
    Prev
    Next
    INDEX
    Explanations

    Average True Range (ATR)

    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_6_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
     dlatego
    0.78
     měli
    0.76
     следует
    0.74
     был
    0.73
    एस
    0.72
     эти
    0.71
     இது
    0.69
     دلیل
    0.68
     *}
    0.68
     ഈ
    0.67
    POSITIVE LOGITS
    the
    1.27
    ات
    0.88
    be
    0.87
    1
    0.86
    ि
    0.86
    да
    0.84
    मी
    0.84
    nya
    0.83
    as
    0.80
    的
    0.80
    Activations Density 0.000%

    No Known Activations