© 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. 75235
    Prev
    Next
    INDEX
    Explanations

    condition disclosure contingency search

    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
     crossover
    0.36
     conducts
    0.34
     tack
    0.34
     adj
    0.33
     dollars
    0.32
     /[
    0.32
     autocor
    0.32
    atenated
    0.32
     crossovers
    0.32
    וע
    0.31
    POSITIVE LOGITS
     மறை
    0.38
    čnost
    0.37
    石頭
    0.37
     камень
    0.36
     phleg
    0.35
    Durante
    0.35
     संतु
    0.35
     инструменты
    0.34
    𝙉
    0.34
     ligula
    0.34
    Activations Density 0.000%

    No Known Activations