© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236740
    Prev
    Next
    INDEX
    Explanations

    zip(*)

    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_25_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
     faveur
    0.44
     Taking
    0.41
     gratuite
    0.40
    ｚ
    0.39
     gratuitement
    0.39
    uva
    0.38
     interfere
    0.38
     Gén
    0.38
    elten
    0.37
     निशुल्क
    0.37
    POSITIVE LOGITS
    ഡ
    0.44
    スマ
    0.43
    тур
    0.42
    Гор
    0.42
    Ober
    0.41
    ్యా
    0.41
     joys
    0.41
     whiteboard
    0.41
    PS
    0.40
     rollout
    0.40
    Activations Density 0.000%

    No Known Activations