© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244731
    Prev
    Next
    INDEX
    Explanations

    stats and scores

    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
     pere
    0.39
    百分
    0.38
    %；
    0.38
     lowercase
    0.38
     poroz
    0.38
     percentages
    0.38
     substitution
    0.36
     Cecilia
    0.36
    Pere
    0.36
     disperse
    0.36
    POSITIVE LOGITS
     tranquillity
    0.41
    샷
    0.38
    RPG
    0.38
    Ful
    0.38
    гласно
    0.38
     tranquill
    0.37
     Fitted
    0.37
    ARDS
    0.35
    集
    0.35
    CAM
    0.35
    Activations Density 0.023%

    No Known Activations