© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39642
    Prev
    Next
    INDEX
    Explanations

    hit upon a

    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_11_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
    {
    0.57
    IS
    0.57
    OUS
    0.57
    IUS
    0.51
     Pedersen
    0.51
    OI
    0.50
    P
    0.50
    పాటు
    0.49
    {\
    0.49
     Studien
    0.48
    POSITIVE LOGITS
    מ
    0.70
    ಮ
    0.67
    ಾಟ
    0.66
     ৩
    0.64
    אם
    0.63
    ması
    0.62
     Реги
    0.61
    தி
    0.60
     ორი
    0.60
     quiso
    0.59
    Activations Density 0.013%

    No Known Activations