© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133635
    Prev
    Next
    INDEX
    Explanations

    what you desire

    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_1_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
    ed
    1.22
    יות
    1.13
    iu
    1.02
    i
    1.02
    es
    0.97
    ih
    0.95
    ediat
    0.93
    AG
    0.93
    的情况
    0.91
    ukunft
    0.91
    POSITIVE LOGITS
     is
    1.70
     of
    1.30
    ные
    1.29
     have
    1.28
     are
    1.21
    <0x0D>
    1.16
    nya
    1.11
    ın
    1.05
     has
    1.02
    1.02
    Activations Density 0.003%

    No Known Activations