© 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. 145607
    Prev
    Next
    INDEX
    Explanations

    sentence

    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
    has
    1.16
    τ
    1.07
    ع
    1.05
    朤
    1.05
    el
    1.04
    ل
    1.03
    kaan
    1.00
    ע
    0.98
     рассказа
    0.97
    有可能
    0.96
    POSITIVE LOGITS
    یت
    2.03
     in
    1.73
    म
    1.63
    𝓭
    1.60
    ম
    1.59
    は
    1.59
     of
    1.55
     the
    1.46
    s
    1.41
    sinh
    1.39
    Activations Density 0.005%

    No Known Activations