© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9549
    Prev
    Next
    INDEX
    Explanations

    quality ingredients

    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
     conhecida
    0.45
     جوړونک
    0.43
     imprese
    0.43
     نیشنل
    0.43
    🌂
    0.42
     conhecido
    0.42
     upang
    0.42
     rezult
    0.41
    ږئ
    0.41
     أخرى
    0.41
    POSITIVE LOGITS
    asing
    0.52
    oring
    0.41
    igare
    0.39
    clean
    0.38
    *
    0.38
    ån
    0.37
    ól
    0.37
    hov
    0.37
    row
    0.37
     Detecting
    0.37
    Activations Density 0.007%

    No Known Activations