© 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. 172014
    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_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
    Plant
    0.48
    oubtedly
    0.47
     সম্পাদিত
    0.47
    ందం
    0.47
    лив
    0.46
     করল
    0.45
     বলল
    0.45
    茴
    0.44
     Plant
    0.43
    嫄
    0.42
    POSITIVE LOGITS
     er
    0.51
     ስርዓ
    0.48
     zawod
    0.47
     ra
    0.46
    cake
    0.46
     nas
    0.46
    ା
    0.45
     sne
    0.44
     smo
    0.44
     kap
    0.44
    Activations Density 0.000%

    No Known Activations