© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40374
    Prev
    Next
    INDEX
    Explanations

    explaining problems, biology, data, and answers

    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_11_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
    ancy
    0.47
    Destination
    0.46
     If
    0.46
    Comparison
    0.46
    嶆
    0.45
    enton
    0.43
     It
    0.42
    ंच
    0.42
    It
    0.42
    phas
    0.42
    POSITIVE LOGITS
     коллеги
    0.56
    𐱃
    0.53
     глоба
    0.52
     derivada
    0.52
     colaboradores
    0.52
     romanos
    0.52
    apayati
    0.51
    에요
    0.50
     baos
    0.50
     staat
    0.50
    Activations Density 0.000%

    No Known Activations