© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205790
    Prev
    Next
    INDEX
    Explanations

    cross-sectional or cross-entropy

    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_37_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
    Direction
    0.42
     Cross
    0.37
     ей
    0.37
     כמ
    0.37
     ChromeDriver
    0.36
     Direction
    0.35
     henne
    0.35
    骓
    0.35
     Hor
    0.35
     RasterModelGrid
    0.35
    POSITIVE LOGITS
     በሽታ
    0.41
     çant
    0.40
    结局
    0.38
     রিলি
    0.38
     suelo
    0.37
    句子
    0.37
    쿨
    0.37
    ,(
    0.36
     prologue
    0.36
     triste
    0.36
    Activations Density 0.001%

    No Known Activations