© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153177
    Prev
    Next
    INDEX
    Explanations

    multiple choice questions

    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_23_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
     시간에
    0.44
     рэгістра
    0.42
     sett
    0.42
    Ved
    0.42
     encontraba
    0.41
     운
    0.41
    hunting
    0.40
     கொண்டிருந்த
    0.39
    вою
    0.39
     cyclic
    0.38
    POSITIVE LOGITS
     nhé
    0.44
     ön
    0.43
    嗎
    0.43
     PREFIX
    0.42
    чите
    0.40
    偉
    0.38
     Humanitarian
    0.38
     sobren
    0.38
     Film
    0.38
     வார
    0.38
    Activations Density 0.000%

    No Known Activations