© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12981
    Prev
    Next
    INDEX
    Explanations

    individuals and singularity

    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_13_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
     Romero
    0.32
    Г
    0.32
     Bands
    0.31
     fecha
    0.31
     Pued
    0.31
     usar
    0.30
     Dodgers
    0.30
    kowych
    0.30
    RENGTH
    0.30
    Fecha
    0.30
    POSITIVE LOGITS
     индиви
    0.32
    Individuals
    0.32
     його
    0.31
    า
    0.31
    ας
    0.30
     Individuals
    0.29
    his
    0.29
     пан
    0.29
    individu
    0.28
     زمین
    0.27
    Activations Density 0.066%

    No Known Activations