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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251167
    Prev
    Next
    INDEX
    Explanations

    card 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
     रजिस्ट
    0.38
     syukur
    0.38
    ας
    0.38
    뵙
    0.36
    chessboard
    0.35
     சிக்க
    0.35
    鍍
    0.34
    षेक
    0.34
    诉
    0.34
     card
    0.34
    POSITIVE LOGITS
     face
    0.98
     Face
    0.95
    Face
    0.95
    face
    0.91
     faces
    0.89
     faced
    0.87
     FACE
    0.83
    faces
    0.83
     лице
    0.80
     Faces
    0.79
    Activations Density 0.001%

    No Known Activations