© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81033
    Prev
    Next
    INDEX
    Explanations

    verbo ending in -ar

    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_0_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
    a
    1.88
    o
    1.84
    p
    1.70
    يل
    1.47
    1.41
    com
    1.35
    AN
    1.35
    g
    1.34
    OS
    1.34
    ية
    1.29
    POSITIVE LOGITS
    지
    2.00
    ल
    1.62
    ق
    1.62
    ی
    1.53
    the
    1.45
    ม
    1.45
    ت
    1.42
    ش
    1.38
    트
    1.35
    ب
    1.34
    Activations Density 0.001%

    No Known Activations