© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198487
    Prev
    Next
    INDEX
    Explanations

    nor important

    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_15_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
     Cricket
    0.52
    Cricket
    0.49
     Football
    0.48
     Boys
    0.47
     Symp
    0.47
    啭
    0.46
     cricket
    0.46
    ]')
    0.46
     Futebol
    0.46
    θηκε
    0.46
    POSITIVE LOGITS
     masts
    0.49
     faucets
    0.48
     totalPrice
    0.47
    λαβ
    0.47
     fenders
    0.46
     tarifs
    0.45
     chimneys
    0.45
     envio
    0.44
     управля
    0.43
     tarifas
    0.43
    Activations Density 0.000%

    No Known Activations