© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215749
    Prev
    Next
    INDEX
    Explanations

    quantization

    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_5_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
    2.03
    {
    1.65
    _
    1.35
    .
    1.34
    \
    1.30
    ০০
    1.17
    {:
    1.15
    for
    1.14
     for
    1.13
    ０
    1.13
    POSITIVE LOGITS
    は
    1.91
    是
    1.76
    s
    1.66
    는
    1.62
    h
    1.46
    に
    1.35
    d
    1.34
    ‌ای
    1.33
    س
    1.32
    ون
    1.30
    Activations Density 0.002%

    No Known Activations