© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49088
    Prev
    Next
    INDEX
    Explanations

    He says/argues/writes

    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_31_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
     Oyster
    0.40
    䁂
    0.39
    ობაში
    0.38
     معناها
    0.38
    istler
    0.37
     बो
    0.36
     Thunder
    0.36
     Olive
    0.35
     oyster
    0.35
     ព
    0.35
    POSITIVE LOGITS
    쟈
    0.49
    :”
    0.45
    :“
    0.44
     aportan
    0.41
    :"
    0.40
     "¿
    0.40
     “(
    0.40
    ：“
    0.40
     okup
    0.39
     conforman
    0.39
    Activations Density 0.000%

    No Known Activations