© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53836
    Prev
    Next
    INDEX
    Explanations

    with food pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     accompagnée
    0.42
     disertai
    0.42
     accompagn
    0.42
     acompañada
    0.42
     accomp
    0.39
     她
    0.38
     kèm
    0.38
     acompañado
    0.38
     pove
    0.37
     Jij
    0.37
    POSITIVE LOGITS
     নিম
    0.40
    ravés
    0.37
    kowski
    0.35
     తరువాత
    0.34
    阻塞
    0.34
    沼
    0.34
    odb
    0.34
    lege
    0.34
    لای
    0.34
     আমন্ত্রণ
    0.33
    Activations Density 0.005%

    No Known Activations