© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228285
    Prev
    Next
    INDEX
    Explanations

    ting

    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_6_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
    ’
    1.27
    ET
    1.14
    ย
    1.02
    ES
    1.02
    ING
    0.98
    i
    0.98
    BE
    0.98
    ting
    0.96
    AE
    0.93
    AIN
    0.93
    POSITIVE LOGITS
     یا
    0.96
    すでに
    0.91
    ரியா
    0.89
    いです
    0.88
     لی
    0.86
    ида
    0.86
     nhân
    0.86
    țit
    0.86
     և
    0.86
     ﺍﻟ
    0.85
    Activations Density 0.001%

    No Known Activations