© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30057
    Prev
    Next
    INDEX
    Explanations

    new words, learning, finance, markets

    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_10_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
    ن
    0.57
    س
    0.53
    ام
    0.52
    I
    0.52
    Así
    0.45
    igans
    0.43
    шение
    0.42
    най
    0.41
    intes
    0.41
    INER
    0.41
    POSITIVE LOGITS
    info
    0.54
     nuova
    0.54
     z
    0.53
    other
    0.53
     sotto
    0.52
    that
    0.52
    per
    0.51
     Secondo
    0.51
    list
    0.51
    new
    0.50
    Activations Density 0.011%

    No Known Activations