© 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. 24696
    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
    0.54
     zuen
    0.50
     lingkaran
    0.47
     acest
    0.47
     ovog
    0.47
     tohoto
    0.47
    oo
    0.44
    Ala
    0.44
    ဤ
    0.44
     dette
    0.43
    POSITIVE LOGITS
    当中
    0.50
    啬
    0.46
    ́
    0.46
     прекрасно
    0.45
    遢
    0.45
     увлека
    0.45
     आजमा
    0.43
    <0xAF>
    0.43
     गाइस
    0.43
     spearheaded
    0.43
    Activations Density 0.000%

    No Known Activations