© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90650
    Prev
    Next
    INDEX
    Explanations

    flour

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ر
    0.67
    ش
    0.57
    Ту
    0.51
    ط
    0.50
    سر
    0.50
    سا
    0.48
    р
    0.48
    رو
    0.48
    사
    0.47
    را
    0.47
    POSITIVE LOGITS
    ้ง
    0.61
     בין
    0.56
    ้น
    0.55
    deco
    0.55
     כי
    0.55
    ้ม
    0.53
    ėje
    0.53
    iaxial
    0.53
    stin
    0.52
    ēn
    0.52
    Activations Density 0.000%

    No Known Activations