© 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. 27835
    Prev
    Next
    INDEX
    Explanations

    связаны с

    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
     ಕಾಲ
    0.42
     Dzięki
    0.40
     Jeśli
    0.39
     ########.
    0.38
     कालेज
    0.38
     благодаря
    0.38
     인
    0.37
    哚
    0.37
    垶
    0.36
    .(*
    0.36
    POSITIVE LOGITS
    rotor
    0.38
    straight
    0.37
    seg
    0.36
    çado
    0.34
    kar
    0.34
    rud
    0.34
     Segal
    0.34
    ratio
    0.34
    vacc
    0.34
    ம்ச
    0.34
    Activations Density 0.027%

    No Known Activations