© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168417
    Prev
    Next
    INDEX
    Explanations

    fine amounts and penalties

    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_34_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
    Georges
    0.41
     imediat
    0.38
     সঙ্গীতের
    0.35
     immédi
    0.35
     aéri
    0.34
     विचारक
    0.34
     Georges
    0.34
    閡
    0.34
     redist
    0.33
     immédiatement
    0.33
    POSITIVE LOGITS
     Guid
    0.41
     Trout
    0.40
    ラック
    0.39
     Chilli
    0.39
     Courtney
    0.38
    WP
    0.38
     Cycling
    0.38
     Happy
    0.38
     Passion
    0.38
    جمالي
    0.38
    Activations Density 0.002%

    No Known Activations