© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10051
    Prev
    Next
    INDEX
    Explanations

    ERC standards

    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_13_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
    ে
    0.30
    ција
    0.30
    ி
    0.29
    י
    0.29
    িনিয়ার
    0.29
     නිෂ්පා
    0.29
    ிகி
    0.29
    ਿਕ
    0.28
     FontWeight
    0.27
    لت
    0.27
    POSITIVE LOGITS
     set
    0.31
     making
    0.30
     محسوس
    0.30
    indahkan
    0.30
     pewno
    0.28
     embrace
    0.28
     напомина
    0.27
     B
    0.27
     attainment
    0.27
     вспомина
    0.27
    Activations Density 0.014%

    No Known Activations