© 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. 149593
    Prev
    Next
    INDEX
    Explanations

    Conclusion: contradiction

    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
    ㄼ
    0.41
     preprocess
    0.39
     LPARAM
    0.39
     sisält
    0.39
    lefthar
    0.38
     dplyr
    0.38
     breakpoints
    0.38
     probabilidad
    0.38
     boundingRect
    0.38
     യുവ
    0.38
    POSITIVE LOGITS
    ^{
    0.39
    constr
    0.37
    стов
    0.35
    łem
    0.34
    ^
    0.34
    Å
    0.33
     French
    0.33
     França
    0.32
    Sever
    0.32
    ϊ
    0.32
    Activations Density 0.000%

    No Known Activations