© 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. 127702
    Prev
    Next
    INDEX
    Explanations

    optimizers and datasets

    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
    unt
    0.59
     you
    0.58
    ў
    0.56
    oL
    0.55
     लिए
    0.55
    agnetic
    0.55
     लकड़ी
    0.55
    er
    0.54
     شہادت
    0.54
     tuoi
    0.54
    POSITIVE LOGITS
    f
    0.77
    b
    0.75
    ק
    0.74
    '
    0.69
    ق
    0.69
    ي
    0.63
    ম
    0.60
    daki
    0.59
    ból
    0.59
    中
    0.57
    Activations Density 0.000%

    No Known Activations