© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52387
    Prev
    Next
    INDEX
    Explanations

    not received

    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
     синх
    0.39
    Д
    0.38
     क्योंकि
    0.38
    because
    0.38
     ஏனெனில்
    0.37
     Porque
    0.36
    크
    0.36
     because
    0.36
     porque
    0.36
    徵
    0.35
    POSITIVE LOGITS
     already
    0.39
    ເລັກ
    0.38
     entire
    0.38
    ঙ্গার
    0.36
     hems
    0.36
     banane
    0.35
     Manager
    0.35
    reso
    0.35
     unaltered
    0.35
    未
    0.35
    Activations Density 0.003%

    No Known Activations