© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134635
    Prev
    Next
    INDEX
    Explanations

    attributable to

    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_6_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
    to
    1.23
    '
    0.88
    то
    0.88
    ’
    0.88
    (
    0.80
     to
    0.71
    ot
    0.71
    ta
    0.64
    ut
    0.63
    ur
    0.61
    POSITIVE LOGITS
    𝗲
    0.67
    ում
    0.67
    ة
    0.64
     Архів
    0.63
     reflexión
    0.63
    ী
    0.63
    𝗴
    0.63
    个
    0.63
     Αυ
    0.62
    comers
    0.62
    Activations Density 0.000%

    No Known Activations