© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210028
    Prev
    Next
    INDEX
    Explanations

    interface

    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_43_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
    xbet
    0.37
    চে
    0.35
    തെന്ന്
    0.34
    Filter
    0.34
    ++',
    0.34
     lentement
    0.33
     multiplying
    0.33
     parlare
    0.33
     Slowly
    0.33
    ivă
    0.33
    POSITIVE LOGITS
     Heim
    0.44
    点で
    0.42
    items
    0.41
    楡
    0.40
     point
    0.40
    安
    0.38
    निया
    0.38
     points
    0.37
     punto
    0.37
    遇
    0.36
    Activations Density 0.006%

    No Known Activations