© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30869
    Prev
    Next
    INDEX
    Explanations

    sounds plausible

    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_31_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
     Canonical
    0.38
     Sterile
    0.38
     Holy
    0.37
    ᅪ
    0.37
     subray
    0.35
     bang
    0.34
     हाथी
    0.33
     Цер
    0.33
     ster
    0.33
     nast
    0.33
    POSITIVE LOGITS
    ┇
    0.40
     род
    0.40
    觉得
    0.40
     native
    0.40
    native
    0.40
     órg
    0.39
    enfance
    0.39
    localhost
    0.39
     déjà
    0.39
     ऑलरेडी
    0.39
    Activations Density 0.093%

    No Known Activations