© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86486
    Prev
    Next
    INDEX
    Explanations

    to-do list generation

    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_18_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
     Lant
    0.50
     laborales
    0.48
     تړ
    0.46
     Changel
    0.46
    ິດຕ
    0.45
    蹇
    0.44
     liegen
    0.44
    埌
    0.44
     plötzlich
    0.44
    क्षिप्त
    0.43
    POSITIVE LOGITS
     shows
    0.48
     bows
    0.47
     bubbles
    0.46
     analysis
    0.45
    вы
    0.44
    shows
    0.43
    muestra
    0.43
     показывает
    0.43
    sce
    0.42
     diamonds
    0.42
    Activations Density 0.004%

    No Known Activations