© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66274
    Prev
    Next
    INDEX
    Explanations

    game changer

    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_41_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
    ួក
    0.37
    ديد
    0.35
    reduction
    0.35
    ับสน
    0.34
    Czechoslovakia
    0.33
    <0xB1>
    0.33
    вается
    0.33
    ظیم
    0.33
    langle
    0.33
    \|+\
    0.33
    POSITIVE LOGITS
     changing
    1.99
     Changing
    1.95
    Changing
    1.91
     changed
    1.88
    改变
    1.82
     changer
    1.80
     cambiar
    1.80
     change
    1.79
     Change
    1.73
    changing
    1.70
    Activations Density 0.005%

    No Known Activations