© 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. 129286
    Prev
    Next
    INDEX
    Explanations

    hax, hap, haff, appe, aught

    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
    ग
    1.16
    >
    1.16
    d
    1.09
    д
    1.09
    It
    1.05
    ים
    1.05
    기
    1.04
    자
    1.03
    다
    1.02
    א
    0.99
    POSITIVE LOGITS
    יות
    0.94
    يط
    0.91
    牦
    0.79
     acus
    0.79
    ة
    0.77
     вересня
    0.75
    نع
    0.73
     vélo
    0.72
    то
    0.71
    bien
    0.71
    Activations Density 0.000%

    No Known Activations