© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40754
    Prev
    Next
    INDEX
    Explanations

    Details

    np_max-act-logits · gemini-2.5-flash-lite
    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
    Negative Logits
    ી
    0.39
     parcial
    0.38
    i
    0.38
    ിച്ച്
    0.37
     Partial
    0.37
    ">−</
    0.37
    筐
    0.37
    ి
    0.36
    ህ
    0.36
    beginTransaction
    0.35
    POSITIVE LOGITS
    Details
    0.80
     Details
    0.61
    ونَ
    0.58
    details
    0.56
     details
    0.55
    DETAILS
    0.55
     détails
    0.52
    ATORY
    0.51
     detalhes
    0.50
     DETAILS
    0.48
    Activations Density 0.021%

    No Known Activations