© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213763
    Prev
    Next
    INDEX
    Explanations

    percentile

    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_5_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
    ס
    1.63
    ל
    1.61
    ת
    1.54
    ון
    1.47
    л
    1.39
    ك
    1.38
    ية
    1.31
    ה
    1.31
    は
    1.30
    מ
    1.30
    POSITIVE LOGITS
    0
    1.61
    ler
    1.14
    ng
    1.09
    reg
    1.08
    ther
    1.06
    law
    1.05
    ram
    1.05
    work
    1.04
    .
    1.04
    ifting
    1.03
    Activations Density 0.000%

    No Known Activations