© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214609
    Prev
    Next
    INDEX
    Explanations

    desperately need or trying

    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_5_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
    يا
    0.60
    ياة
    0.60
     élargies
    0.56
    場合は
    0.55
     الجيش
    0.55
     reflexión
    0.54
    ק
    0.54
    いません
    0.54
    ல்
    0.54
     ομάδα
    0.54
    POSITIVE LOGITS
    o
    1.31
    a
    1.30
    p
    1.13
    e
    1.07
    y
    1.04
    i
    0.94
    ed
    0.91
    er
    0.88
    t
    0.86
    um
    0.84
    Activations Density 0.011%

    No Known Activations