© 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. 207812
    Prev
    Next
    INDEX
    Explanations

    feature

    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
    MouseMove
    0.40
     svr
    0.40
    getSign
    0.39
     rang
    0.39
     Peptide
    0.39
     محاضرت
    0.38
    ᡵ
    0.38
     Sommer
    0.38
    遊
    0.37
    archa
    0.37
    POSITIVE LOGITS
     motivation
    0.45
     motivations
    0.43
     motivates
    0.40
    Motivation
    0.40
    motiv
    0.39
     dishonesty
    0.38
    Configurer
    0.38
     motiv
    0.37
    动机
    0.37
     motivated
    0.37
    Activations Density 0.003%

    No Known Activations