© 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. 210428
    Prev
    Next
    INDEX
    Explanations

    HTML parsing

    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
     карка
    0.50
     پیپلز
    0.43
    ടിക്ക
    0.43
    éges
    0.41
    𒂊
    0.41
    сну
    0.41
    ವಾಡ
    0.41
    സു
    0.40
    لې
    0.40
    framework
    0.40
    POSITIVE LOGITS
     và
    0.46
     සහ
    0.45
     κα
    0.44
     व
    0.44
     και
    0.44
     trophic
    0.43
     dichotom
    0.43
     dominance
    0.43
    和
    0.42
     уголов
    0.42
    Activations Density 0.001%

    No Known Activations