© 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. 134257
    Prev
    Next
    INDEX
    Explanations

    moisture on skin or in air

    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
    ↵
    1.34
     for
    1.26
    ла
    1.25
    ль
    1.10
    ล
    1.09
     провер
    1.05
    <0xA8>
    1.02
    то
    1.02
    ми
    1.00
    ו
    1.00
    POSITIVE LOGITS
    は
    1.30
    ll
    1.24
    는
    1.13
     is
    1.12
    কে
    1.06
    lands
    1.03
    은
    1.00
    が
    0.97
    高く
    0.97
    २
    0.95
    Activations Density 0.001%

    No Known Activations