© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206297
    Prev
    Next
    INDEX
    Explanations

    divisors of number

    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_20_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
    ူ
    0.22
     Applications
    0.21
     miscellaneous
    0.21
     uygulam
    0.21
     aplik
    0.20
     severally
    0.20
     allere
    0.20
     Application
    0.19
     erros
    0.19
     klik
    0.19
    POSITIVE LOGITS
    がる
    0.21
    怛
    0.21
    𝓢
    0.21
    ectable
    0.20
    ेंद्रीय
    0.20
     suficientes
    0.20
     tamaños
    0.20
    𝙃
    0.19
     মিসেস
    0.19
     рациона
    0.19
    Activations Density 0.005%

    No Known Activations