© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60709
    Prev
    Next
    INDEX
    Explanations

    uniform resource names

    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_2_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
     for
    1.46
    is
    1.30
    in
    1.09
     from
    1.09
    的光
    1.00
     Identifier
    0.98
     of
    0.95
    m
    0.95
    ِّف
    0.94
    T
    0.94
    POSITIVE LOGITS
    ك
    1.45
    も
    1.41
    る
    1.38
     an
    1.30
    ו
    1.23
    و
    1.22
     are
    1.21
    ا
    1.14
    י
    1.13
     są
    1.11
    Activations Density 0.001%

    No Known Activations