© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141847
    Prev
    Next
    INDEX
    Explanations

    tapestries

    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
     is
    1.98
    ка
    1.92
    ك
    1.79
    ف
    1.75
    ,
    1.63
    г
    1.54
    𝙨
    1.43
    م
    1.38
    ق
    1.34
    ா
    1.30
    POSITIVE LOGITS
     for
    2.42
    al
    1.30
     with
    1.23
    ৮
    1.23
     (
    1.20
     If
    1.13
    1.09
     It
    1.08
    ட்சத்திர
    1.06
    ۹
    1.05
    Activations Density 0.003%

    No Known Activations