© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9956
    Prev
    Next
    INDEX
    Explanations

    spatial shape

    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_40_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
     mapping
    0.41
    omerase
    0.40
     Mapping
    0.37
     Wurzel
    0.37
    梫
    0.37
     Rhe
    0.36
     CheckKey
    0.36
    yto
    0.35
    有没有
    0.35
     phrases
    0.34
    POSITIVE LOGITS
     layer
    0.72
    Layer
    0.69
     Layer
    0.67
    層
    0.64
    layer
    0.62
     Layers
    0.61
     layers
    0.61
     shape
    0.59
    层
    0.59
    shape
    0.58
    Activations Density 0.050%

    No Known Activations