© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194357
    Prev
    Next
    INDEX
    Explanations

    directory, page

    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_9_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
     tensão
    0.50
     hoặc
    0.50
     với
    0.50
     ẞ
    0.49
    [*][[
    0.48
    adilan
    0.48
    anın
    0.47
     gás
    0.47
    urança
    0.47
     lên
    0.47
    POSITIVE LOGITS
     заро
    0.47
    Disponible
    0.47
    特
    0.46
    百科
    0.45
    OGRAM
    0.45
     दुर्लभ
    0.44
    Экс
    0.43
    oin
    0.43
    spraak
    0.43
    そもそも
    0.43
    Activations Density 0.000%

    No Known Activations