© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137771
    Prev
    Next
    INDEX
    Explanations

    Qatar, Egypt, December

    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_12_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
    l
    0.52
    ed
    0.47
    ాల్
    0.47
    AH
    0.46
    Department
    0.45
     Doha
    0.44
    BIO
    0.44
    8
    0.43
     II
    0.42
     قطر
    0.42
    POSITIVE LOGITS
     தனி
    0.56
     完全
    0.50
    tpVar
    0.50
     Knut
    0.49
    "{@
    0.49
    veri
    0.48
     個人
    0.47
    vastatin
    0.47
    они
    0.45
    temporal
    0.45
    Activations Density 0.014%

    No Known Activations