© 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. 108531
    Prev
    Next
    INDEX
    Explanations

    uye

    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
    r
    1.78
     on
    1.58
    h
    1.52
    s
    1.51
    é
    1.29
    j
    1.26
    v
    1.24
    ag
    1.23
    t
    1.21
    。
    1.21
    POSITIVE LOGITS
    י
    2.08
    ン
    1.41
    ו
    1.39
    ي
    1.34
    на
    1.31
    า
    1.31
    Мо
    1.27
    ック
    1.24
    のは
    1.22
     וא
    1.21
    Activations Density 0.000%

    No Known Activations