© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106303
    Prev
    Next
    INDEX
    Explanations

    Smithsonian Magazine

    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
    2
    1.41
    ד
    1.21
    t
    1.10
    нга
    1.05
    1
    1.04
    :
    1.02
    ;
    0.94
    For
    0.90
    '
    0.88
    dal
    0.86
    POSITIVE LOGITS
     is
    1.30
    ോഷ്യ
    1.27
    า
    1.24
    ле
    1.23
    த்தில்
    1.16
     a
    1.13
    ik
    1.11
    á
    1.10
     나
    1.09
    е
    1.06
    Activations Density 0.001%

    No Known Activations