© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217692
    Prev
    Next
    INDEX
    Explanations

    Worcestershire

    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_50_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
     nas
    0.41
    as
    0.40
    ﾉ
    0.40
     Harden
    0.40
    tered
    0.40
    tern
    0.39
     chi
    0.39
    terne
    0.38
     Hertz
    0.38
     L
    0.38
    POSITIVE LOGITS
    OTTOM
    0.42
    Apa
    0.41
     النسبيه
    0.41
    RI
    0.38
    Capt
    0.38
    ரி
    0.38
     Dalmat
    0.38
    capt
    0.37
    烛
    0.37
     Apa
    0.37
    Activations Density 0.000%

    No Known Activations