© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120549
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

    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_38_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
     layer
    1.72
    layer
    1.45
     слой
    1.44
     thin
    1.38
     layers
    1.36
    层
    1.35
    層
    1.35
    Layer
    1.34
     Layer
    1.34
     LAYER
    1.33
    POSITIVE LOGITS
    addock
    0.40
     upgrading
    0.38
     senator
    0.38
     NG
    0.38
     кло
    0.37
    apest
    0.36
    ∟
    0.36
     ե
    0.35
    əs
    0.35
     upgrades
    0.35
    Activations Density 0.050%

    No Known Activations