© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159516
    Prev
    Next
    INDEX
    Explanations

    homogeneous recovery, coordinates, mixture, equation

    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_2_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
    し
    1.52
    \
    1.30
    ре
    1.27
    ление
    1.27
    ુ
    1.23
    يل
    1.19
    εται
    1.18
     préférable
    1.18
    ется
    1.16
    िस
    1.14
    POSITIVE LOGITS
    y
    2.22
    a
    2.14
    in
    2.02
    p
    1.92
    i
    1.87
    n
    1.80
    0
    1.72
    is
    1.69
    il
    1.63
    g
    1.58
    Activations Density 0.001%

    No Known Activations