© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133128
    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_6_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
    {
    0.82
    ra
    0.76
    if
    0.68
    আ
    0.65
    ana
    0.64
    kan
    0.64
    पाकिस्तान
    0.64
    as
    0.64
    you
    0.64
    <?
    0.63
    POSITIVE LOGITS
     sphing
    0.51
     distillate
    0.50
     broth
    0.49
     burrito
    0.49
     cle
    0.48
     regimen
    0.48
     feedstock
    0.48
     heave
    0.47
     grease
    0.47
     pact
    0.47
    Activations Density 0.000%

    No Known Activations