© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62430
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ς
    1.16
    s
    0.97
    ?
    0.85
    (
    0.82
    λη
    0.76
    italization
    0.70
    리
    0.70
    φάλ
    0.70
    !
    0.69
    ul
    0.68
    POSITIVE LOGITS
    ت
    1.71
    m
    1.29
    ম
    1.27
    ী
    1.07
    ת
    1.03
    ە
    1.00
    ק
    1.00
    b
    1.00
    מ
    0.98
    ו
    0.98
    Activations Density 0.000%

    No Known Activations