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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6173
    Prev
    Next
    INDEX
    Explanations

    version codes or identifiers

    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_40_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
    ∟
    0.42
    ller
    0.40
     Impacts
    0.39
    ⁻
    0.38
    ર્મા
    0.38
     Rtl
    0.37
     ফেরার
    0.37
    ยม
    0.37
     todd
    0.37
     Yol
    0.37
    POSITIVE LOGITS
     ০১
    0.42
    Feb
    0.40
    できません
    0.39
     ০৯
    0.37
     ещё
    0.36
    ția
    0.35
    Lon
    0.35
     тяжё
    0.34
    泛
    0.34
     honors
    0.34
    Activations Density 0.035%

    No Known Activations