© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53752
    Prev
    Next
    INDEX
    Explanations

    json structures, dictionaries, and code snippets

    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_31_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
    ART
    0.28
    Enc
    0.26
    レス
    0.25
     *.
    0.25
    MILL
    0.25
     रॉय
    0.24
    fal
    0.24
    完整的
    0.24
     hashing
    0.24
     Enc
    0.23
    POSITIVE LOGITS
     BlueprintName
    0.29
    setWidth
    0.28
     pressur
    0.28
     Subsect
    0.27
     allah
    0.27
    bmi
    0.26
     ತುಂಬಾ
    0.26
     같아요
    0.26
    
    0.26
     NM
    0.25
    Activations Density 0.004%

    No Known Activations