© 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. 60616
    Prev
    Next
    INDEX
    Explanations

    ub, du

    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
    et
    1.55
    ت
    1.24
     It
    1.17
    n
    1.12
    ن
    1.09
    ת
    1.08
    ре
    1.07
    р
    1.06
    os
    1.05
    <0x80>
    1.02
    POSITIVE LOGITS
    EK
    1.13
    듀
    1.08
    Ду
    1.03
    Du
    0.98
    du
    0.97
    지
    0.97
    can
    0.96
    ud
    0.95
     dụng
    0.95
    I
    0.95
    Activations Density 0.004%

    No Known Activations