© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207139
    Prev
    Next
    INDEX
    Explanations

    few-shot examples

    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_19_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
    ণিজ
    0.30
    㐫
    0.28
     woke
    0.28
    硙
    0.28
     cStart
    0.27
     refunds
    0.27
     όχι
    0.26
    وہ
    0.26
     '[
    0.26
    gaon
    0.26
    POSITIVE LOGITS
    circum
    0.28
    D
    0.28
    rem
    0.27
    டக
    0.27
    explanatory
    0.27
    스트
    0.26
    conservation
    0.26
     cuadrada
    0.26
    بعة
    0.26
    AL
    0.26
    Activations Density 0.103%

    No Known Activations