© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13845
    Prev
    Next
    INDEX
    Explanations

    java class definitions

    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_15_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
     \
    0.31
    k
    0.30
    कारी
    0.28
     ك
    0.28
    j
    0.27
    к
    0.27
     ક
    0.26
    ک
    0.26
    ؟
    0.26
     ಕರಿ
    0.26
    POSITIVE LOGITS
    美好
    0.26
    弘
    0.25
     slightly
    0.23
    糹
    0.23
     gotta
    0.23
    ，
    0.23
     svých
    0.22
    Businessman
    0.22
     spad
    0.22
     don
    0.22
    Activations Density 0.002%

    No Known Activations