© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50382
    Prev
    Next
    INDEX
    Explanations

    explaining definitions or results

    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_10_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
    ারে
    0.48
    നിന്ന്
    0.47
    檤
    0.47
    ευ
    0.44
    BeerItem
    0.43
    <0xBA>
    0.43
    érez
    0.43
     तेज़
    0.42
    ंतर
    0.42
    ദാ
    0.42
    POSITIVE LOGITS
    w
    0.54
    W
    0.52
     выполня
    0.50
    dummies
    0.49
     alkaloids
    0.48
    security
    0.48
    Isometric
    0.48
    require
    0.47
    dotnet
    0.47
    cline
    0.46
    Activations Density 0.000%

    No Known Activations