© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30905
    Prev
    Next
    INDEX
    Explanations

    GRID size

    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_31_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
    បញ្ចប់
    0.41
     ఘ
    0.39
    ГУ
    0.38
     ([[
    0.37
    怡
    0.36
     നിറഞ്ഞ
    0.36
    )(=
    0.36
     JSONArray
    0.35
     @@
    0.35
     घटा
    0.35
    POSITIVE LOGITS
     służ
    0.37
    ngthening
    0.37
     Dimensional
    0.37
     broadening
    0.36
     broaden
    0.36
     GRAN
    0.36
     Strengthening
    0.35
     አማ
    0.35
     Grain
    0.35
    inspired
    0.34
    Activations Density 0.005%

    No Known Activations