© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160151
    Prev
    Next
    INDEX
    Explanations

    годы, годов, того

    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_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
     I
    1.43
    Ｉ
    1.07
     It
    0.99
    ale
    0.99
    gi
    0.98
    vis
    0.98
    ong
    0.97
     In
    0.97
    I
    0.97
     (
    0.96
    POSITIVE LOGITS
    ת
    1.45
    א
    1.43
    تين
    1.41
    י
    1.34
    ק
    1.27
    ב
    1.26
    تون
    1.23
    ке
    1.23
    ت
    1.23
    る
    1.16
    Activations Density 0.000%

    No Known Activations