© 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. 59126
    Prev
    Next
    INDEX
    Explanations

    sparring

    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
    ב
    1.38
    но
    1.27
    b
    1.26
    Z
    1.23
    y
    1.22
    נ
    1.21
    あらゆる
    1.17
    мо
    1.16
    С
    1.16
    ла
    1.15
    POSITIVE LOGITS
    ted
    1.11
    tn
    1.07
    te
    1.05
    0
    0.97
    kannya
    0.96
    tet
    0.94
    \
    0.91
     restitu
    0.91
     have
    0.90
    ama
    0.89
    Activations Density 0.001%

    No Known Activations