© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245821
    Prev
    Next
    INDEX
    Explanations

    grams per pound of body weight

    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_40_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
    ギ
    0.42
     Tests
    0.39
     day
    0.39
     tests
    0.39
     TESTS
    0.39
    椷
    0.39
    减
    0.38
     ingest
    0.38
    阵
    0.37
     Day
    0.36
    POSITIVE LOGITS
    \\.
    0.41
     fusible
    0.40
    Filename
    0.40
    readable
    0.39
     interpreting
    0.39
     పాల
    0.39
    Pall
    0.39
     leggere
    0.39
     palladium
    0.38
     reprint
    0.38
    Activations Density 0.003%

    No Known Activations