© 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. 171959
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Гре
    0.51
    닛
    0.45
    コンテンツ
    0.45
    idcoin
    0.44
    સી
    0.44
     शाय
    0.44
    Ꭰ
    0.44
    景观
    0.43
    راہیم
    0.43
    妠
    0.43
    POSITIVE LOGITS
    his
    0.45
     đảm
    0.41
    boolean
    0.40
    OR
    0.40
    assert
    0.40
     exhausting
    0.40
     upper
    0.39
    ensure
    0.39
     Algebra
    0.38
     basic
    0.38
    Activations Density 0.000%

    No Known Activations