© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44808
    Prev
    Next
    INDEX
    Explanations

    let's do it

    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
    0.44
    ড
    0.40
    рів
    0.39
     ت
    0.39
     screen
    0.39
    ρων
    0.37
    ructure
    0.37
    Levels
    0.37
    Aware
    0.37
    曜
    0.37
    POSITIVE LOGITS
    ște
    0.46
     Chesterfield
    0.43
     gratuitamente
    0.42
     vuttam
    0.40
     Đông
    0.40
    historic
    0.39
    izde
    0.39
     THEM
    0.38
     futuros
    0.38
    ಿಯಾಗಿ
    0.38
    Activations Density 0.150%

    No Known Activations