© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13884
    Prev
    Next
    INDEX
    Explanations

    serving size

    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_15_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
     know
    0.55
     savoir
    0.54
    Learn
    0.53
    A
    0.53
    tp
    0.53
    When
    0.52
     tapi
    0.52
    è
    0.52
     yung
    0.51
    ā
    0.51
    POSITIVE LOGITS
     filede
    0.63
     большо
    0.60
     發
    0.59
     фай
    0.58
     bactéri
    0.58
     fileCopy
    0.55
    ODBA
    0.55
     克
    0.55
     Leib
    0.54
     ファイル
    0.54
    Activations Density 0.004%

    No Known Activations