© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30806
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and drawing commands

    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_31_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
     aversion
    0.31
    গরে
    0.31
    왤
    0.30
     semic
    0.29
    borist
    0.29
    Nguyen
    0.29
    ёг
    0.29
    Synced
    0.29
     Face
    0.29
     tann
    0.29
    POSITIVE LOGITS
     влия
    0.29
     rips
    0.29
     förs
    0.28
     thinks
    0.27
    茧
    0.27
    音楽
    0.27
    তেই
    0.27
     തുറ
    0.26
     نشست
    0.26
    낚
    0.26
    Activations Density 0.005%

    No Known Activations