© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     المسافه
    0.45
     Kommunikation
    0.44
     wisata
    0.44
     possibilidade
    0.44
     Gestión
    0.44
     Trabajo
    0.43
     manusia
    0.43
    渺
    0.42
     hjäl
    0.42
    人类
    0.42
    POSITIVE LOGITS
    ft
    0.54
    ulfill
    0.49
     griev
    0.49
    야
    0.49
    1
    0.47
    mill
    0.46
    in
    0.46
     ದಿನ
    0.46
    ointment
    0.45
     미국
    0.45
    Activations Density 0.000%

    No Known Activations