© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81747
    Prev
    Next
    INDEX
    Explanations

    Apache software projects

    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_0_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
    1.72
    h
    1.59
    О
    1.21
    y
    1.20
     \
    1.10
    на
    1.10
    Ν
    1.10
    x
    1.09
     Montessori
    1.07
     (\
    1.05
    POSITIVE LOGITS
    ка
    1.52
    ك
    1.45
    ன்
    1.38
    ছে
    1.38
    is
    1.30
    ان
    1.30
    هي
    1.29
    ้
    1.29
    し
    1.27
    ே
    1.23
    Activations Density 0.001%

    No Known Activations