© 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. 211467
    Prev
    Next
    INDEX
    Explanations

    function/method definitions

    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
     impos
    0.28
     cannabinoids
    0.28
     Soldiers
    0.26
    铤
    0.26
     impatiently
    0.25
    ]=\
    0.25
     CallOptions
    0.25
     chevaux
    0.24
    獲
    0.24
     usur
    0.24
    POSITIVE LOGITS
    Ⲛ
    0.29
    وا
    0.27
     النبات
    0.27
    群体
    0.27
    イ
    0.27
    وني
    0.26
    中国的
    0.26
    nga
    0.26
    modation
    0.26
    فك
    0.26
    Activations Density 0.000%

    No Known Activations