© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42758
    Prev
    Next
    INDEX
    Explanations

    script after canvas

    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
     предоставля
    0.23
    iin
    0.22
    $/../../../../
    0.21
     previously
    0.21
     promises
    0.21
    最终
    0.21
     রাক
    0.20
     برقرار
    0.20
     appeals
    0.20
     باسم
    0.20
    POSITIVE LOGITS
    cep
    0.25
    ComponentModel
    0.23
     timbre
    0.23
    荷重
    0.22
     ഇന്ത്യൻ
    0.22
    
    0.22
     Всё
    0.21
     දු
    0.21
    之所以
    0.21
     Chandigarh
    0.21
    Activations Density 0.005%

    No Known Activations