© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210916
    Prev
    Next
    INDEX
    Explanations

    reshape data

    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_20_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
    äude
    0.51
    ích
    0.47
    liferation
    0.47
     имају
    0.46
    "):
    0.45
     desigualdad
    0.45
     رجسٹ
    0.43
     緑
    0.43
    𒃻
    0.43
    ponente
    0.42
    POSITIVE LOGITS
     honeymoon
    0.46
     bridge
    0.43
    ówn
    0.43
     jasper
    0.42
     Jasper
    0.39
    &#
    0.39
     state
    0.39
     John
    0.39
    nth
    0.39
     Twe
    0.39
    Activations Density 0.001%

    No Known Activations