© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107311
    Prev
    Next
    INDEX
    Explanations

    after "they" verbs

    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_1_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
    c
    0.98
     =
    0.93
     is
    0.82
     has
    0.80
    ש
    0.77
    to
    0.75
     uczni
    0.75
     be
    0.73
     у
    0.73
    기
    0.71
    POSITIVE LOGITS
    '
    1.17
    :
    1.05
    ig
    0.93
    8
    0.87
    ä
    0.86
    ,
    0.77
    -
    0.73
    6
    0.70
    7
    0.69
    9
    0.68
    Activations Density 0.010%

    No Known Activations