© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93328
    Prev
    Next
    INDEX
    Explanations

    unflattering, flattering

    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
    𝐞
    0.69
    ro
    0.68
    er
    0.64
    ل
    0.64
    l
    0.63
     to
    0.63
     computer
    0.63
     kontrol
    0.61
     U
    0.59
    lt
    0.59
    POSITIVE LOGITS
    convén
    0.54
    必要があります
    0.54
    ౪
    0.54
     તેમ
    0.53
    接地
    0.53
    щен
    0.52
     مثل
    0.52
     ефектив
    0.52
    образ
    0.51
     кең
    0.51
    Activations Density 0.001%

    No Known Activations