© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45951
    Prev
    Next
    INDEX
    Explanations

    isochronic tones, hypocrates, isoquants

    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_3_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
     o
    0.91
     e
    0.81
     in
    0.73
     as
    0.65
     (
    0.63
     et
    0.61
    </h3>
    0.60
     meter
    0.60
     i
    0.58
     er
    0.57
    POSITIVE LOGITS
    an
    1.00
    و
    0.88
    ن
    0.86
    މ
    0.86
    не
    0.85
    os
    0.84
    with
    0.84
     latérales
    0.84
    jhelp
    0.80
    roits
    0.80
    Activations Density 0.009%

    No Known Activations