© 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. 24734
    Prev
    Next
    INDEX
    Explanations

    fine suffix and related words

    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
    0.81
    ك
    0.81
    مو
    0.80
    isering
    0.76
    ان
    0.72
    می
    0.70
     rares
    0.69
    ه
    0.69
    ո
    0.69
    etting
    0.68
    POSITIVE LOGITS
    ING
    0.75
     +
    0.73
     welche
    0.72
     -
    0.66
    ִי
    0.65
     +"
    0.64
     [
    0.63
    ta
    0.63
     zum
    0.62
     PAUL
    0.61
    Activations Density 0.001%

    No Known Activations