© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45639
    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_22_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
     predict
    0.48
     stew
    0.45
     interpolate
    0.45
     interpolated
    0.44
    た
    0.44
    да
    0.43
    ta
    0.43
     DESC
    0.43
    アシ
    0.43
    타
    0.42
    POSITIVE LOGITS
     SupCt
    0.47
    LOTREntity
    0.46
    发生
    0.46
    ন্‌
    0.45
    若是
    0.45
     TNumber
    0.44
    ВД
    0.44
     खुलने
    0.44
     শিক্ষা
    0.44
     timescales
    0.44
    Activations Density 0.000%

    No Known Activations