© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254167
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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
    Negative Logits
     unbreakable
    0.39
    glob
    0.36
     moguć
    0.35
    量
    0.35
    াশ
    0.35
     dotted
    0.34
     popular
    0.34
     underserved
    0.34
    TryParse
    0.33
    dct
    0.32
    POSITIVE LOGITS
     :
    0.60
     :-
    0.54
     ;
    0.48
     :#
    0.46
    -”
    0.46
    :”
    0.42
     ;-
    0.42
    :-
    0.42
     shielding
    0.41
     कहता
    0.41
    Activations Density 0.003%

    No Known Activations