© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32733
    Prev
    Next
    INDEX
    Explanations

    `t` followed by programming terms

    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_7_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
    و
    0.50
    все
    0.39
     allgemeinen
    0.38
    ל
    0.38
    Jeśli
    0.38
    Didn
    0.37
    šao
    0.36
    첫
    0.36
    dokka
    0.35
    쳤
    0.35
    POSITIVE LOGITS
     are
    0.75
     of
    0.74
     is
    0.67
     be
    0.57
    ă
    0.49
     with
    0.48
     have
    0.46
    t
    0.46
     has
    0.46
     ने
    0.43
    Activations Density 0.010%

    No Known Activations