© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201085
    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
    饉
    0.42
     stylus
    0.40
     invers
    0.40
    antan
    0.40
     analysts
    0.39
     Idam
    0.37
    ρης
    0.36
     stanu
    0.36
    iyama
    0.35
     manages
    0.35
    POSITIVE LOGITS
     fortalecer
    0.41
     priestly
    0.41
     cref
    0.39
    枧
    0.39
    瓠
    0.38
    adjoint
    0.38
    housing
    0.38
    pbx
    0.37
    דת
    0.37
     dvar
    0.36
    Activations Density 0.000%

    No Known Activations