© 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. 232674
    Prev
    Next
    INDEX
    Explanations

    fl- followed by common word endings

    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
    ;
    1.33
    ння
    1.18
    ς
    1.05
    s
    1.00
    اد
    0.96
    ابي
    0.93
    нер
    0.93
    ха
    0.89
    ние
    0.89
    ,
    0.87
    POSITIVE LOGITS
    एस
    1.26
    い
    1.15
    एम
    1.09
    at
    1.05
    et
    1.05
    el
    1.02
    টি
    1.00
    io
    0.96
    У
    0.96
    IT
    0.96
    Activations Density 0.002%

    No Known Activations