© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1513
    Prev
    Next
    INDEX
    Explanations

    Oracle cloud free search

    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_39_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
     double
    0.39
     MOD
    0.37
     Double
    0.35
     चयन
    0.35
     DOUBLE
    0.35
     Nazi
    0.34
     trademark
    0.34
    笆
    0.34
     nap
    0.34
     Broad
    0.34
    POSITIVE LOGITS
    Buildings
    0.39
    Tau
    0.37
    cau
    0.34
    Pok
    0.33
     takePhotoButton
    0.33
    фикации
    0.33
    דת
    0.32
    קה
    0.32
    ၣ်
    0.32
    Repositories
    0.32
    Activations Density 0.002%

    No Known Activations