© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40166
    Prev
    Next
    INDEX
    Explanations

    clothing descriptors

    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_57_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
    Coff
    0.43
    Ｃ
    0.42
     Kuch
    0.40
    Ч
    0.40
     Dunk
    0.40
     Shank
    0.39
    Kuch
    0.38
     Dun
    0.38
    relation
    0.38
    Kane
    0.38
    POSITIVE LOGITS
     v
    0.53
     ia
    0.43
     overall
    0.42
     ا
    0.41
     aven
    0.40
     vi
    0.40
     كس
    0.39
     claus
    0.39
     wear
    0.38
     fusion
    0.38
    Activations Density 0.010%

    No Known Activations