© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83604
    Prev
    Next
    INDEX
    Explanations

    scott felt, scott decision, scott speed

    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_0_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
    ز
    1.85
    其他
    1.57
    л
    1.51
    م
    1.41
    و
    1.35
    ल
    1.32
    高
    1.30
    لل
    1.27
    うまく
    1.26
     पढ़ाई
    1.21
    POSITIVE LOGITS
    та
    1.75
    ים
    1.44
    них
    1.25
    ьте
    1.20
    ター
    1.19
    तून
    1.19
    ۰۰
    1.14
    ंद
    1.13
     auxin
    1.13
    s
    1.13
    Activations Density 0.000%

    No Known Activations