© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130585
    Prev
    Next
    INDEX
    Explanations

    deserts and dinosaurs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    대는
    0.38
     ಕಿ
    0.37
    にし
    0.36
    祁
    0.35
     કિ
    0.35
    عداد
    0.34
    阌
    0.34
     nob
    0.34
    ήθ
    0.34
    撕
    0.34
    POSITIVE LOGITS
     Cle
    0.44
     Crop
    0.43
     Cro
    0.42
     Alonzo
    0.42
     Chef
    0.40
     Auctions
    0.40
     champs
    0.40
     Authent
    0.40
     Auction
    0.39
     الدم
    0.39
    Activations Density 0.000%

    No Known Activations