© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24736
    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_10_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
    <0x0D>
    0.58
     шли
    0.54
     ")
    0.52
     ATPase
    0.52
     ﺍ
    0.52
     artistdata
    0.51
    вёр
    0.51
    <unused988>
    0.51
    <unused2019>
    0.50
     пришли
    0.50
    POSITIVE LOGITS
     terrible
    0.55
     family
    0.54
     como
    0.51
     week
    0.51
     horrible
    0.51
     conspicuous
    0.50
     mut
    0.50
     good
    0.50
     ineffective
    0.50
     terrific
    0.48
    Activations Density 0.000%

    No Known Activations