© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206764
    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gl
    0.39
     éto
    0.38
    ధ్య
    0.37
     enjoined
    0.37
    闡
    0.36
     authorised
    0.36
     உதாரணமாக
    0.35
    奉
    0.35
     authorized
    0.34
     글
    0.34
    POSITIVE LOGITS
    outines
    0.41
    atres
    0.40
    atever
    0.40
    okh
    0.40
    asam
    0.39
    ahay
    0.39
    енера
    0.39
     Hays
    0.39
    🍏
    0.39
    igma
    0.37
    Activations Density 0.000%

    No Known Activations