© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143529
    Prev
    Next
    INDEX
    Explanations

    Technical configuration/settings

    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_46_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
    啠
    0.42
    કુ
    0.39
    authority
    0.38
    romed
    0.38
    вій
    0.37
    にな
    0.37
    ރު
    0.37
     ด
    0.37
     Authority
    0.37
    advanced
    0.37
    POSITIVE LOGITS
     Georgia
    0.37
     Jean
    0.37
    Georgia
    0.36
    OCE
    0.36
     Corners
    0.33
     Tri
    0.33
     jean
    0.33
    urna
    0.33
    یدن
    0.33
    独
    0.33
    Activations Density 0.000%

    No Known Activations