© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45896
    Prev
    Next
    INDEX
    Explanations

    compass direction

    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_13_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
    نه
    0.47
     camino
    0.47
     phasing
    0.47
    Boundary
    0.46
    的环境
    0.46
    dés
    0.45
    캉
    0.45
    ى
    0.45
     పరిస్థి
    0.45
     Transportation
    0.44
    POSITIVE LOGITS
    Quran
    0.60
     Tinder
    0.59
     n
    0.59
    startsWith
    0.55
    Соцмережа
    0.54
     suure
    0.54
    ולים
    0.54
    Ⲡ
    0.53
    conten
    0.52
     фирмы
    0.52
    Activations Density 0.023%

    No Known Activations