© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78136
    Prev
    Next
    INDEX
    Explanations

    harsh / harsher

    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_0_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
    ul
    1.85
    d
    1.64
    एस
    1.52
    AC
    1.49
    TES
    1.46
    AA
    1.43
    ER
    1.41
    m
    1.41
    SP
    1.39
    ad
    1.38
    POSITIVE LOGITS
    ٨
    1.36
    ре
    1.30
    ९
    1.27
    {
    1.25
    ί
    1.23
    си
    1.22
    ८
    1.21
    ?
    1.20
    ру
    1.19
    рі
    1.16
    Activations Density 0.002%

    No Known Activations