© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58190
    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_2_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
    ي
    1.66
    י
    1.48
    i
    1.45
    ו
    1.34
    ت
    1.27
    t
    1.25
    it
    1.13
    iu
    1.04
    en
    1.02
    os
    1.02
    POSITIVE LOGITS
    _
    1.13
    <0x80>
    1.01
     godine
    0.98
     godziny
    0.96
     montaña
    0.94
     aastal
    0.91
     Tahun
    0.90
     ocasi
    0.90
    ();
    0.90
    ss
    0.89
    Activations Density 0.000%

    No Known Activations