© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197527
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and commands

    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_26_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
     (
    0.35
    Analysis
    0.33
    entraînement
    0.32
     Management
    0.32
     quits
    0.31
    ከል
    0.31
    <start_of_image>
    0.31
     analysis
    0.31
    피
    0.31
     고
    0.30
    POSITIVE LOGITS
     producir
    0.43
     ahorro
    0.40
     RESP
    0.40
     escapar
    0.39
     almeno
    0.38
     फाइनेंशियल
    0.38
     SPAC
    0.37
     ارب
    0.37
    asun
    0.37
     økonom
    0.37
    Activations Density 0.000%

    No Known Activations