© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53430
    Prev
    Next
    INDEX
    Explanations

    element.style/classList manipulation

    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_31_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
    ᚄ
    0.29
    🥒
    0.27
     قط
    0.27
    LOSS
    0.26
    UIServer
    0.26
    Scan
    0.25
    THON
    0.25
     SCAN
    0.25
    istle
    0.25
    ⛷
    0.25
    POSITIVE LOGITS
     longitudinally
    0.29
    benz
    0.29
    lag
    0.28
     longitudinal
    0.28
     ya
    0.28
     America
    0.27
     young
    0.26
     developing
    0.26
     amateurs
    0.26
     Longitudinal
    0.26
    Activations Density 0.002%

    No Known Activations