© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217895
    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_16_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
     étend
    0.48
    rafts
    0.46
    𝚛
    0.45
    uous
    0.45
     simplex
    0.45
     varie
    0.44
    iremos
    0.44
     pruning
    0.44
    Coat
    0.43
     bloques
    0.43
    POSITIVE LOGITS
    ປະ
    0.50
    インター
    0.49
     Nasir
    0.48
    お
    0.46
    aphosa
    0.45
     и
    0.45
     Iraqi
    0.44
     ಸಾ
    0.43
    RTC
    0.43
     аны
    0.43
    Activations Density 0.000%

    No Known Activations