© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239685
    Prev
    Next
    INDEX
    Explanations

    integer types declaration

    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_25_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
    ülü
    0.36
     tình
    0.34
    弃
    0.34
     neg
    0.34
    dart
    0.34
     charity
    0.34
     крити
    0.34
    Disp
    0.34
    〃
    0.34
    टिक
    0.33
    POSITIVE LOGITS
     dupla
    0.44
     algunas
    0.44
    裡面
    0.43
     وہاں
    0.43
    いく
    0.41
    allelujah
    0.40
     Beaucoup
    0.40
     mój
    0.40
    Ⴊ
    0.39
    밤
    0.39
    Activations Density 0.000%

    No Known Activations