© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36124
    Prev
    Next
    INDEX
    Explanations

    sensor float values

    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_11_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
     ಉತ್ತಮ
    0.52
    igste
    0.52
    ithin
    0.51
     tradition
    0.49
     전통
    0.49
     neighbor
    0.48
     redistribution
    0.48
     :}
    0.47
    <0x98>
    0.46
     ?
    0.46
    POSITIVE LOGITS
    Según
    0.65
    Solo
    0.61
    Estos
    0.59
    İlk
    0.59
     occas
    0.59
    Moj
    0.58
    Jeśli
    0.57
    Después
    0.57
    Nicole
    0.57
    São
    0.56
    Activations Density 0.001%

    No Known Activations