© 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. 220633
    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
     Indica
    0.54
     intramuscular
    0.52
     isoform
    0.51
     데이터
    0.50
     unforeseen
    0.50
     독일
    0.48
    )');
    0.48
     의견
    0.48
     Seja
    0.48
    乳
    0.48
    POSITIVE LOGITS
    Sheep
    0.50
    path
    0.50
    Peru
    0.50
    ul
    0.49
    Siempre
    0.49
    ment
    0.46
    much
    0.46
    align
    0.46
    batt
    0.46
    Tesla
    0.46
    Activations Density 0.000%

    No Known Activations