© 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. 158872
    Prev
    Next
    INDEX
    Explanations

    A

    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
    那么
    0.40
    কমার্স
    0.40
     mercury
    0.39
    ,_-
    0.38
    ్యూ
    0.38
    玤
    0.38
    addEdge
    0.37
     subcutaneous
    0.37
    ዪ
    0.36
     HPV
    0.36
    POSITIVE LOGITS
    Pat
    0.42
    Mult
    0.41
    Building
    0.41
    Tracking
    0.40
    FTR
    0.39
    Plant
    0.39
    CTE
    0.39
    heter
    0.39
    rop
    0.38
    Hot
    0.38
    Activations Density 0.001%

    No Known Activations