© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198150
    Prev
    Next
    INDEX
    Explanations

    where in

    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_12_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
    ین
    0.44
    ம்
    0.41
    م
    0.40
    м
    0.39
    ו
    0.37
     rumbo
    0.37
     gioc
    0.36
    ת
    0.35
    し
    0.34
    as
    0.34
    POSITIVE LOGITS
     Boosting
    0.39
     Patients
    0.38
     i
    0.37
     arv
    0.37
    "):
    0.37
     Patient
    0.36
     Reducing
    0.36
     Enhance
    0.36
     Improvement
    0.35
     Sandwich
    0.35
    Activations Density 0.000%

    No Known Activations