© 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. 41729
    Prev
    Next
    INDEX
    Explanations

    delta, ΔT

    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
    '
    1.05
    \
    0.96
    (
    0.71
    হ
    0.66
    <
    0.66
    ↵
    0.64
     It
    0.62
    ल
    0.61
    л
    0.60
    kon
    0.60
    POSITIVE LOGITS
     delta
    0.86
    is
    0.79
     delt
    0.75
    ing
    0.70
    ed
    0.70
     scrutinized
    0.67
     وګټ
    0.65
     jeopardize
    0.64
     accentuate
    0.64
    يرا
    0.63
    Activations Density 0.020%

    No Known Activations