© 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. 130034
    Prev
    Next
    INDEX
    Explanations

    sedimentation rate, arthritis, hemorrhage, cocktail, bleeding

    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
    and
    1.48
    in
    1.15
    for
    1.11
    at
    1.09
    mén
    1.08
     raffin
    1.07
    n
    1.07
    i
    1.05
    with
    1.03
    pady
    0.99
    POSITIVE LOGITS
     are
    1.95
     it
    1.38
    й
    1.35
    ।
    1.27
     as
    1.23
    л
    1.23
     są
    1.16
    ö
    1.16
    ç
    1.12
    ?
    1.11
    Activations Density 0.013%

    No Known Activations