© 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. 171460
    Prev
    Next
    INDEX
    Explanations

    code duplication and complexity

    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
    alk
    0.44
     ith
    0.43
    hospital
    0.41
    ith
    0.41
    re
    0.39
    ren
    0.39
    τι
    0.39
    z
    0.39
    assertEqual
    0.39
    Disconnected
    0.39
    POSITIVE LOGITS
    ᡠ
    0.46
     रीजनिंग
    0.45
     ねえ
    0.44
    ępow
    0.43
     базу
    0.43
    pecu
    0.43
     रखती
    0.43
     निसाब
    0.42
    ♗
    0.42
     ਉਹ
    0.42
    Activations Density 0.003%

    No Known Activations