© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143603
    Prev
    Next
    INDEX
    Explanations

    Bill

    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_0_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
    ك
    1.34
    كيد
    1.30
    getCQL
    1.20
    كيل
    1.20
    话
    1.16
    il
    1.15
    ங்க
    1.13
    好吃
    1.11
    不够
    1.09
    ⺀
    1.09
    POSITIVE LOGITS
     is
    2.30
    は
    2.03
    l
    1.85
    '
    1.85
    n
    1.80
    $
    1.63
    )
    1.61
    은
    1.48
    st
    1.47
    是
    1.45
    Activations Density 0.000%

    No Known Activations