© 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. 75228
    Prev
    Next
    INDEX
    Explanations

    overclocking

    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
    ফর্ম
    0.31
    ClassLoader
    0.31
    Max
    0.31
    ỏng
    0.31
     virtualization
    0.31
    农村
    0.30
    戞
    0.30
     without
    0.30
    Extension
    0.30
     slots
    0.30
    POSITIVE LOGITS
     Leeds
    0.34
     mill
    0.32
    默
    0.31
     tremor
    0.31
     ga
    0.31
     cid
    0.31
    Leeds
    0.31
     whitew
    0.30
     inputValue
    0.30
     Irishman
    0.30
    Activations Density 0.071%

    No Known Activations