© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23612
    Prev
    Next
    INDEX
    Explanations

    faces

    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_56_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
     ре
    1.09
    re
    1.07
    RE
    0.95
     re
    0.91
     RE
    0.86
     재
    0.82
     Re
    0.72
     pro
    0.64
    재
    0.64
     PRO
    0.61
    POSITIVE LOGITS
     Face
    0.65
    Face
    0.62
     face
    0.61
    臉
    0.58
    脸
    0.57
    face
    0.54
     faces
    0.53
     FACE
    0.51
    フェイス
    0.48
    faces
    0.48
    Activations Density 0.011%

    No Known Activations