© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210719
    Prev
    Next
    INDEX
    Explanations

    manage to

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Date
    0.13
    antal
    0.12
    ራ
    0.12
    еди
    0.12
    रे
    0.12
     Date
    0.12
     rnorm
    0.12
    ரோ
    0.11
    лён
    0.11
    colFirst
    0.11
    POSITIVE LOGITS
     vš
    0.14
     подклю
    0.14
     पुस्तकों
    0.14
    ՛
    0.13
    🅷
    0.13
     shortened
    0.13
     植物
    0.13
     ils
    0.12
     poured
    0.12
     Goodreads
    0.12
    Activations Density 0.008%

    No Known Activations