© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125165
    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_37_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
     രണ്ടു
    0.38
    RadioButton
    0.38
    umab
    0.37
    Pant
    0.37
    Nab
    0.36
    覦
    0.36
    cante
    0.36
    Pda
    0.36
    DID
    0.36
     الفصل
    0.35
    POSITIVE LOGITS
     легко
    0.55
     fácilmente
    0.53
     fácil
    0.52
     easily
    0.50
    慥
    0.46
    容易
    0.46
     aisément
    0.46
     fáciles
    0.45
    ⣤
    0.43
     facilement
    0.43
    Activations Density 0.000%

    No Known Activations