© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16882
    Prev
    Next
    INDEX
    Explanations

    initial -

    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_40_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
     repetition
    0.41
     Predictive
    0.36
     kis
    0.36
     saves
    0.35
    (_)
    0.34
     an
    0.34
     justified
    0.34
    Sav
    0.34
     epi
    0.34
     ততক্ষণ
    0.34
    POSITIVE LOGITS
    емом
    0.41
    teborg
    0.40
    ümüş
    0.39
    суль
    0.38
    娍
    0.38
    stackpath
    0.38
    ◜
    0.38
     Krebs
    0.37
    ײ
    0.37
    щин
    0.37
    Activations Density 0.001%

    No Known Activations