© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49011
    Prev
    Next
    INDEX
    Explanations

    spatial and positional terms

    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_31_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
    tokenId
    0.39
    Token
    0.36
    ibe
    0.36
     पदार्थ
    0.36
     धाराओं
    0.36
    豆
    0.35
    ican
    0.35
    Array
    0.34
    <<
    0.34
    ток
    0.33
    POSITIVE LOGITS
     McCullough
    0.39
    ướ
    0.39
    retryWrites
    0.38
    ettamente
    0.37
     suivie
    0.37
    。（
    0.37
    बरी
    0.36
     ២
    0.36
     Kumb
    0.36
    哆
    0.36
    Activations Density 0.007%

    No Known Activations