© 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. 51777
    Prev
    Next
    INDEX
    Explanations

    looping through DataFrame rows

    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
    डील
    0.35
     суда
    0.35
    笫
    0.35
     innermost
    0.35
     מז
    0.35
     евре
    0.34
    ेबल
    0.34
    Uz
    0.33
    رحله
    0.33
     İm
    0.33
    POSITIVE LOGITS
     Stars
    0.39
     heightened
    0.38
     tourne
    0.37
    Coroutine
    0.37
     gols
    0.37
     olsun
    0.37
     k
    0.36
     tropical
    0.36
     Bin
    0.36
    TaskManager
    0.36
    Activations Density 0.045%

    No Known Activations