© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90169
    Prev
    Next
    INDEX
    Explanations

    weight classes

    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_23_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
    TrackAngle
    0.48
     tölt
    0.41
     związku
    0.40
    ณฑ
    0.39
    鑫
    0.39
    nection
    0.38
     élect
    0.38
    linien
    0.38
    नाथ
    0.37
    noDB
    0.37
    POSITIVE LOGITS
    class
    0.39
     Cayman
    0.36
    らった
    0.36
     খোঁ
    0.36
    ceived
    0.36
    category
    0.35
    ائط
    0.35
     Cheetah
    0.35
     Rotating
    0.35
     $(-
    0.35
    Activations Density 0.000%

    No Known Activations