© 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. 28674
    Prev
    Next
    INDEX
    Explanations

    technically or techniques

    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
    ت
    0.75
    та
    0.73
     بر
    0.68
    ק
    0.66
    nání
    0.65
    andosi
    0.64
    техни
    0.63
    ോ
    0.63
     след
    0.62
     Wro
    0.62
    POSITIVE LOGITS
    p
    0.78
     are
    0.62
     of
    0.57
    യില
    0.55
    de
    0.52
     iterations
    0.52
     parable
    0.51
     TECHNIQUES
    0.51
    姨
    0.51
     they
    0.50
    Activations Density 0.011%

    No Known Activations