© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60080
    Prev
    Next
    INDEX
    Explanations

    Arabic language

    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_59_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
     **,
    0.40
    LH
    0.38
    V
    0.38
     S
    0.37
    ER
    0.37
     BMS
    0.37
     eroded
    0.37
     Shuang
    0.36
     “,
    0.36
    **,
    0.35
    POSITIVE LOGITS
    datat
    0.48
    hapi
    0.48
    wot
    0.46
    ȇ
    0.46
    াসেব
    0.46
    зите
    0.45
    ᴡ
    0.44
    köy
    0.43
    ḏ
    0.43
    including
    0.43
    Activations Density 0.001%

    No Known Activations