© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140353
    Prev
    Next
    INDEX
    Explanations

    associate

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     cnt
    0.42
     chiefs
    0.39
    徃
    0.39
     персонал
    0.38
    ографи
    0.38
     fast
    0.37
     அலுவலக
    0.37
    র্ভাব
    0.37
     office
    0.37
     চীৎকার
    0.37
    POSITIVE LOGITS
     provider
    0.38
    ক্রান্ত
    0.37
    Detector
    0.37
     Woodford
    0.36
     wood
    0.36
    澧
    0.36
    ριν
    0.36
    Wiley
    0.35
     explorer
    0.35
    PLEMENT
    0.34
    Activations Density 0.000%

    No Known Activations