© 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. 175276
    Prev
    Next
    INDEX
    Explanations

    pairing, drawing, seeding, random assignment

    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
    slate
    0.41
     სახელმწიფ
    0.41
     આન
    0.40
    羪
    0.39
    נן
    0.38
    мовір
    0.38
    㗆
    0.38
    ペン
    0.38
     Gandh
    0.38
    ोने
    0.37
    POSITIVE LOGITS
     resulted
    0.46
    सद
    0.45
     stuck
    0.44
     répét
    0.43
     blossomed
    0.43
     transitive
    0.42
     récip
    0.41
    anı
    0.41
     placée
    0.41
     representatives
    0.41
    Activations Density 0.000%

    No Known Activations