© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207571
    Prev
    Next
    INDEX
    Explanations

    facial anatomy

    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
    Negative Logits
     Morse
    0.38
     ACID
    0.37
    𝚂
    0.37
     ಎಸ್
    0.37
     Waffen
    0.36
    楲
    0.36
    hão
    0.35
     Haines
    0.35
    量
    0.35
     acid
    0.34
    POSITIVE LOGITS
     ար
    0.46
    hexane
    0.45
    ారం
    0.40
    basic
    0.39
    放
    0.39
    izen
    0.38
    吸引
    0.38
     Paran
    0.38
     PROC
    0.38
     neurons
    0.37
    Activations Density 0.003%

    No Known Activations