© 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. 32145
    Prev
    Next
    INDEX
    Explanations

    top universities in China

    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
    рово
    0.40
    嘲
    0.39
     Stove
    0.39
     FEBRUARY
    0.38
     CCM
    0.37
    ///////////
    0.37
    Overview
    0.37
    cking
    0.37
    菰
    0.37
     McM
    0.37
    POSITIVE LOGITS
    double
    0.38
    Ens
    0.37
    endig
    0.36
     tes
    0.35
     ausgezeichnet
    0.35
    الى
    0.35
    蒈
    0.34
    <unused84>
    0.34
    tes
    0.34
    тиву
    0.34
    Activations Density 0.010%

    No Known Activations