© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45514
    Prev
    Next
    INDEX
    Explanations

    command-line flags and function calls

    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_22_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
    त्तियों
    0.26
    ំហ
    0.23
    ᅡ
    0.21
     హైదర్
    0.21
     infraestructura
    0.21
     colaborar
    0.20
    য়াছে
    0.20
     strutture
    0.20
     Sys
    0.20
     universitaire
    0.20
    POSITIVE LOGITS
     міс
    0.25
     گیند
    0.20
     stimulated
    0.19
    匣
    0.19
    戝
    0.19
    of
    0.19
     gă
    0.19
     വരു
    0.19
    current
    0.19
    ห
    0.19
    Activations Density 0.002%

    No Known Activations