© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211612
    Prev
    Next
    INDEX
    Explanations

    optimization problems

    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_20_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
    слава
    0.48
    邾
    0.46
    ും
    0.45
     Beginning
    0.45
     Venue
    0.45
     Prison
    0.44
     swirl
    0.43
     নেই
    0.43
     गर्दन
    0.43
    渐渐
    0.43
    POSITIVE LOGITS
     irre
    0.42
    тых
    0.42
     preco
    0.40
     ehe
    0.38
     positif
    0.38
    ध
    0.37
     bystanders
    0.37
     onlookers
    0.37
    テ
    0.37
    لاث
    0.36
    Activations Density 0.000%

    No Known Activations