© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176105
    Prev
    Next
    INDEX
    Explanations

    Chocolate and cinnamon flavors

    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_20_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
    рованным
    0.36
    報
    0.31
    вшим
    0.29
    出力
    0.28
    嘯
    0.27
     henceforth
    0.27
     имя
    0.26
    视为
    0.26
     bese
    0.26
     除
    0.26
    POSITIVE LOGITS
    angwa
    0.36
    iquement
    0.36
    ଖ
    0.33
     altijd
    0.33
     bijvoorbeeld
    0.32
     Unter
    0.32
    ity
    0.31
    wicket
    0.31
     струк
    0.31
    Unter
    0.31
    Activations Density 0.004%

    No Known Activations