© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38458
    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_57_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
    цах
    0.41
    ουμε
    0.36
     tái
    0.35
    浏
    0.35
    iyama
    0.35
    bore
    0.35
    入院
    0.34
    VariableName
    0.34
    BEFORE
    0.34
     extiende
    0.34
    POSITIVE LOGITS
     जै
    0.38
    Coord
    0.38
     bait
    0.37
     коро
    0.36
    дет
    0.36
     Orth
    0.36
     Imo
    0.36
     Pltf
    0.36
    快
    0.36
     جعفر
    0.35
    Activations Density 0.000%

    No Known Activations