© 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. 171960
    Prev
    Next
    INDEX
    Explanations

    tongs, forklift, forms

    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
     Schools
    0.39
    Schools
    0.37
    aya
    0.36
     Ether
    0.35
    ᱖
    0.35
    fora
    0.34
    竞争
    0.33
     کامیاب
    0.33
     Gin
    0.32
     Goldman
    0.32
    POSITIVE LOGITS
     🤔
    0.37
     mili
    0.36
     وش
    0.34
     doss
    0.34
    зу
    0.33
     scand
    0.33
     mascot
    0.32
     upris
    0.32
    ᕐ
    0.32
     such
    0.32
    Activations Density 0.001%

    No Known Activations