© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16535
    Prev
    Next
    INDEX
    Explanations

    history

    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
     defined
    0.38
     has
    0.38
     still
    0.37
    \
    0.37
     patients
    0.36
    лис
    0.36
     future
    0.35
     defining
    0.35
     needs
    0.35
    する場合
    0.34
    POSITIVE LOGITS
    Nazi
    0.44
    NCc
    0.40
     खेलों
    0.37
     Stie
    0.37
    cessing
    0.37
    芏
    0.37
    FAR
    0.37
    ﻪ
    0.37
    platte
    0.36
    ASE
    0.36
    Activations Density 0.041%

    No Known Activations