© 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. 49349
    Prev
    Next
    INDEX
    Explanations

    Virginia Woolf

    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
    dden
    0.45
    عر
    0.37
    sning
    0.37
     DataLoader
    0.36
    덱
    0.36
     Gambit
    0.35
    ensuremath
    0.35
    шов
    0.35
     Últ
    0.34
    רים
    0.34
    POSITIVE LOGITS
     suces
    0.42
    Flu
    0.39
    части
    0.38
     pej
    0.38
     పే
    0.37
    脉
    0.37
     nort
    0.36
     न्यूजीलैंड
    0.35
     свър
    0.35
    Weather
    0.34
    Activations Density 0.005%

    No Known Activations