© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215427
    Prev
    Next
    INDEX
    Explanations

    method or process

    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_31_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
    ichero
    0.33
     unsatisfactory
    0.32
    叽
    0.31
     insp
    0.31
     inventors
    0.31
    imes
    0.30
    ጐ
    0.30
     tests
    0.30
    oos
    0.30
    sadpoetry
    0.30
    POSITIVE LOGITS
    kilomet
    0.34
    בא
    0.32
     Май
    0.30
     учет
    0.30
    困难
    0.29
    ))}{
    0.29
    困難
    0.29
     निय
    0.28
     matemat
    0.28
     एप
    0.28
    Activations Density 0.002%

    No Known Activations