© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106845
    Prev
    Next
    INDEX
    Explanations

    München or remuneration

    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_2_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
    al
    1.53
    :
    1.31
    +
    1.18
     i
    0.96
    -
    0.90
    dominal
    0.89
    dine
    0.89
    ,
    0.89
    ové
    0.85
    /
    0.85
    POSITIVE LOGITS
    ق
    1.99
    ب
    1.82
    م
    1.74
    ه
    1.56
    خ
    1.55
    ف
    1.53
    ك
    1.52
    ו
    1.41
    m
    1.37
    است
    1.33
    Activations Density 0.000%

    No Known Activations