© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25741
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    <0x0D>
    0.54
    primary
    0.54
    slightly
    0.53
    Plasma
    0.52
    ccgi
    0.52
    two
    0.50
    pera
    0.50
    iguiente
    0.50
     Еще
    0.49
     cinquième
    0.49
    POSITIVE LOGITS
    轰
    0.46
     propulsion
    0.46
    当年
    0.43
    ่วน
    0.43
     Powers
    0.42
     motor
    0.42
    轟
    0.42
    时
    0.41
     factorization
    0.39
     décès
    0.39
    Activations Density 0.000%

    No Known Activations