© 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. 144707
    Prev
    Next
    INDEX
    Explanations

    missing kids

    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
    n
    2.47
    ン
    1.94
    م
    1.91
    न
    1.82
    ल
    1.70
    l
    1.62
    m
    1.59
    н
    1.58
    ת
    1.56
    p
    1.54
    POSITIVE LOGITS
    та
    1.55
     و
    1.37
    的设计
    1.32
    ’,
    1.22
     и
    1.21
     have
    1.18
    </h3>
    1.15
    </h6>
    1.15
    れて
    1.11
    ۰۰
    1.10
    Activations Density 0.001%

    No Known Activations