© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88770
    Prev
    Next
    INDEX
    Explanations

    撥

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    修
    0.85
     修
    0.60
    俢
    0.50
    脩
    0.41
     root
    0.35
    鉴
    0.35
    ದ
    0.34
     अंशु
    0.34
     Complimentary
    0.33
    _{(
    0.32
    POSITIVE LOGITS
    さ
    2.38
     さ
    1.32
     са
    1.30
     sa
    1.16
    さは
    1.14
     Sa
    1.08
    Sa
    1.07
     사
    1.03
     सा
    1.01
     سا
    1.01
    Activations Density 0.005%

    No Known Activations