© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17412
    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_34_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
    oxet
    0.36
    Expecting
    0.35
     обеща
    0.35
    Line
    0.35
    ટા
    0.34
     оцени
    0.34
     intending
    0.34
    |\
    0.33
     Requested
    0.33
    кистон
    0.33
    POSITIVE LOGITS
    ibilität
    0.41
    iddish
    0.39
    喑
    0.38
    單
    0.38
    honor
    0.36
    ర్కొ
    0.36
    δει
    0.35
    ख्त
    0.35
    後半
    0.34
     கொள்ளலாம்
    0.34
    Activations Density 0.000%

    No Known Activations