© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37506
    Prev
    Next
    INDEX
    Explanations

    grass types and seasons

    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_11_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
    ס
    0.40
    ت
    0.36
    س
    0.34
     ר
    0.34
    ಿದ್ದೇವೆ
    0.34
     them
    0.33
    ج
    0.33
    四个
    0.32
    弹性
    0.32
    all
    0.32
    POSITIVE LOGITS
    㫜
    0.37
    嘰
    0.36
    idcoin
    0.35
     Congr
    0.35
     alertas
    0.35
    둣
    0.34
     diny
    0.34
     conteú
    0.33
     mostra
    0.33
    cena
    0.33
    Activations Density 0.002%

    No Known Activations