© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44501
    Prev
    Next
    INDEX
    Explanations

    cricket formats Test ODI

    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
     العام
    0.22
    ানী
    0.20
    ются
    0.19
     Ricardo
    0.19
    с
    0.19
    alet
    0.19
    лайте
    0.18
    暧
    0.18
     написано
    0.18
    认证
    0.18
    POSITIVE LOGITS
     جري
    0.23
     ٣
    0.22
    
    0.22
     vivir
    0.22
     attrition
    0.22
     Stiftung
    0.21
     삼
    0.21
     conteú
    0.21
     quán
    0.21
    glial
    0.21
    Activations Density 0.001%

    No Known Activations