© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33157
    Prev
    Next
    INDEX
    Explanations

    csv file

    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_40_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
    (/(
    0.36
     صحبت
    0.35
    ][/
    0.33
    માન
    0.32
    気になる
    0.32
    病情
    0.32
     birbirinden
    0.32
    เต
    0.32
     संथाल
    0.32
    лору
    0.32
    POSITIVE LOGITS
    涀
    0.38
     besteht
    0.36
     Merid
    0.35
     nati
    0.35
    
    0.34
    らう
    0.34
    ﾞ
    0.34
    ardı
    0.33
    尽
    0.33
     Shan
    0.33
    Activations Density 0.204%

    No Known Activations