© 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. 171265
    Prev
    Next
    INDEX
    Explanations

    can

    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
     Universit
    0.38
     referrerpolicy
    0.37
    charset
    0.37
     м
    0.36
     :::
    0.36
     faccio
    0.35
     Lieut
    0.35
     jPanel
    0.35
     евре
    0.35
    ાગ
    0.34
    POSITIVE LOGITS
     cant
    0.77
    dont
    0.68
     dont
    0.66
     Cant
    0.66
    cant
    0.64
    Dont
    0.63
     Dont
    0.59
     '
    0.58
     didnt
    0.57
    Cant
    0.57
    Activations Density 0.002%

    No Known Activations