© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102796
    Prev
    Next
    INDEX
    Explanations

    album published

    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_1_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
     to
    1.55
    ،
    1.46
     be
    1.41
    it
    1.41
    ור
    1.36
    ี
    1.27
    س
    1.25
    то
    1.23
    ir
    1.22
    いますが
    1.22
    POSITIVE LOGITS
    ya
    1.33
    h
    1.17
    v
    1.16
    yaa
    0.89
     as
    0.88
    tr
    0.85
    ties
    0.83
    ci
    0.82
    ని
    0.82
     Biochemical
    0.82
    Activations Density 0.000%

    No Known Activations