© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42367
    Prev
    Next
    INDEX
    Explanations

    tongue-in-cheek

    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
    ظر
    0.52
    /')
    0.48
     fordi
    0.48
    ர
    0.47
    жая
    0.44
    /\
    0.44
    вто
    0.43
    وس
    0.42
     regel
    0.42
    /");
    0.42
    POSITIVE LOGITS
     judges
    0.49
     healthiest
    0.45
     pube
    0.44
     germination
    0.43
    ↵
    0.43
     piena
    0.43
     guérir
    0.43
     bills
    0.42
     judged
    0.42
     instinct
    0.42
    Activations Density 0.001%

    No Known Activations