© 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. 84588
    Prev
    Next
    INDEX
    Explanations

    stripping away

    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
    Not in Any Lists

    No Comments

    Negative Logits
    barui
    1.22
    stion
    1.14
     말미암아
    1.12
    ल्लिंग
    1.11
    ामध्ये
    1.10
    ס
    1.09
    peso
    1.08
    ಬ್ಬಿಣ
    1.06
    st
    1.05
    gulation
    1.05
    POSITIVE LOGITS
    т
    1.75
    an
    1.69
    ?
    1.54
    at
    1.52
    ר
    1.50
    ้
    1.46
    э
    1.44
    ar
    1.43
    {
    1.42
    C
    1.38
    Activations Density 0.000%

    No Known Activations