© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138649
    Prev
    Next
    INDEX
    Explanations

    fetish

    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
    Not in Any Lists

    No Comments

    Negative Logits
    philosoph
    0.36
     &__
    0.35
    Optim
    0.34
     Optim
    0.34
    LaunchAction
    0.34
     মাইক্র
    0.34
     Femme
    0.34
     ㅎㅎ
    0.33
     optim
    0.33
     ㅋㅋ
    0.33
    POSITIVE LOGITS
    Ե
    0.44
     posts
    0.40
     materiais
    0.39
    เหน
    0.39
     Mud
    0.39
    材料
    0.39
    posts
    0.38
    Posts
    0.38
     Mudd
    0.38
    Mud
    0.38
    Activations Density 0.004%

    No Known Activations