© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42096
    Prev
    Next
    INDEX
    Explanations

    not followed by contrast

    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_22_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
    ﻙ
    0.29
     יכול
    0.29
     pourraient
    0.29
    ക്കാം
    0.29
     बढ़ा
    0.28
     পারেন
    0.28
    مكن
    0.28
     Merchants
    0.27
     يمكن
    0.27
     三角
    0.27
    POSITIVE LOGITS
    Band
    0.27
    BUL
    0.26
    โ
    0.26
    Day
    0.26
    Device
    0.26
     choked
    0.25
    Ber
    0.25
    Dry
    0.25
    Humidity
    0.25
    Toto
    0.25
    Activations Density 0.021%

    No Known Activations