© 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. 158020
    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
    st
    1.32
    n
    1.30
    ۔
    1.23
    ms
    1.21
    1.19
    se
    1.16
    the
    1.16
    ।
    1.15
    ru
    1.14
    na
    1.14
    POSITIVE LOGITS
    िंग
    1.10
    い
    1.06
     adatto
    1.04
    িয়া
    1.02
     indispensables
    1.02
    ﺖ
    1.02
     arrondies
    1.01
     আত্মীয়
    1.00
    রিষ্ঠ
    0.97
     ottimo
    0.97
    Activations Density 0.000%

    No Known Activations