© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38653
    Prev
    Next
    INDEX
    Explanations

    force attacks, force instead

    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_3_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
     بي
    0.95
     is
    0.87
     سي
    0.83
     هي
    0.81
     as
    0.77
     含
    0.73
     لي
    0.71
     اي
    0.70
     كم
    0.68
     إ
    0.68
    POSITIVE LOGITS
    א
    1.06
    י
    1.05
    ก็
    0.88
    มัน
    0.84
    i
    0.82
    ات
    0.80
    จะ
    0.80
    ి
    0.79
    ব
    0.78
    ים
    0.77
    Activations Density 0.000%

    No Known Activations