© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149971
    Prev
    Next
    INDEX
    Explanations

    releases, requested, Elba, tend

    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_23_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
    医学
    0.46
    㫣
    0.40
     erros
    0.39
    手数料
    0.39
    --’
    0.39
     کرام
    0.39
     orbits
    0.39
    ]$,
    0.38
     Virology
    0.37
     jerseys
    0.37
    POSITIVE LOGITS
    蔷
    0.42
     suele
    0.41
     अहम
    0.41
    Ⲗ
    0.41
    Aff
    0.40
    amalla
    0.40
    обе
    0.39
    ниц
    0.38
     احتاج
    0.38
     tend
    0.37
    Activations Density 0.000%

    No Known Activations