© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43236
    Prev
    Next
    INDEX
    Explanations

    images in markdown

    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_22_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
    Mark
    0.47
    陈
    0.43
    Mat
    0.43
    Мар
    0.43
    IMAGE
    0.43
    Marine
    0.43
    如
    0.42
    쏠
    0.42
    嬉しい
    0.41
    晧
    0.41
    POSITIVE LOGITS
     breathing
    0.42
     breaths
    0.41
     priests
    0.40
     newborn
    0.38
     poisoned
    0.38
     cloud
    0.38
     escape
    0.38
     airborne
    0.38
     position
    0.37
     Failed
    0.37
    Activations Density 0.001%

    No Known Activations