© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7400
    Prev
    Next
    INDEX
    Explanations

    database schema and users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     Breathe
    0.42
     Colombo
    0.41
     plenum
    0.39
     Bres
    0.38
     Frances
    0.38
    Colombo
    0.38
    ককে
    0.38
    侷
    0.38
     café
    0.36
     Rain
    0.36
    POSITIVE LOGITS
    Authorization
    0.43
    AUTHORIZED
    0.39
    Fault
    0.37
     authorisation
    0.37
     emplea
    0.37
    锁
    0.36
    PhotoImage
    0.36
     גר
    0.35
     courant
    0.35
     कंपनी
    0.35
    Activations Density 0.001%

    No Known Activations