© 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. 46653
    Prev
    Next
    INDEX
    Explanations

    la followed by nouns

    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
    :
    0.70
    𒊹
    0.69
    begin
    0.63
    GoObject
    0.63
     Laub
    0.62
    𝒂
    0.61
     a
    0.60
    的部分
    0.60
     Yarm
    0.60
     Doğ
    0.59
    POSITIVE LOGITS
    지
    0.86
    ot
    0.78
    0
    0.75
    uksen
    0.73
    را
    0.71
    지에
    0.70
    akon
    0.70
    ه
    0.69
    ای
    0.68
    em
    0.67
    Activations Density 0.002%

    No Known Activations