© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39725
    Prev
    Next
    INDEX
    Explanations

    follow rules or guidelines

    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_11_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
    ITIES
    0.62
     definisi
    0.59
     Delicate
    0.56
     Defines
    0.54
     settim
    0.53
     Qxa
    0.53
    橦
    0.53
    抔
    0.53
     H
    0.53
    𒄩
    0.53
    POSITIVE LOGITS
    ی
    0.70
    ۵
    0.61
    \
    0.61
    ᱔
    0.59
     practiced
    0.57
    ς
    0.55
    ي
    0.55
    ۔
    0.55
    ါ
    0.55
    ään
    0.54
    Activations Density 0.010%

    No Known Activations