© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178079
    Prev
    Next
    INDEX
    Explanations

    search

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     brisk
    0.38
    붓
    0.36
     tink
    0.36
    inor
    0.36
    了大
    0.35
    ازی
    0.35
    スメ
    0.34
    ཎ
    0.34
     ब्रि
    0.33
     Arag
    0.33
    POSITIVE LOGITS
     cerc
    1.59
     cer
    1.58
     cerca
    1.54
     Cerc
    1.45
    Cer
    1.38
     cercare
    1.37
     Cer
    1.34
    cer
    1.34
    CER
    1.34
     CER
    1.31
    Activations Density 0.000%

    No Known Activations