© 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. 204102
    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
     postępow
    0.41
     {.
    0.41
     Oxidation
    0.40
    ньому
    0.40
     nim
    0.39
    salt
    0.39
     cint
    0.38
     Excav
    0.38
     vle
    0.38
    cstring
    0.38
    POSITIVE LOGITS
     perfectly
    0.42
     المرحله
    0.36
    初
    0.35
     much
    0.34
     Perfectly
    0.34
    putting
    0.34
     المرحلة
    0.34
    ั้ง
    0.33
    ப்பதை
    0.33
    ब्दी
    0.32
    Activations Density 0.000%

    No Known Activations