© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97392
    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_14_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
    Бу
    0.61
    У
    0.55
    Бы
    0.53
    Би
    0.52
    ଢ
    0.52
    㧋
    0.52
    부
    0.51
    Une
    0.50
    আ
    0.49
    เมื่อ
    0.49
    POSITIVE LOGITS
     ç
    0.62
     packs
    0.55
     parad
    0.53
     Grüße
    0.53
     pét
    0.51
     cm
    0.51
     blogs
    0.51
     jähr
    0.50
     sev
    0.50
     commute
    0.49
    Activations Density 0.000%

    No Known Activations