© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111119
    Prev
    Next
    INDEX
    Explanations

    gun

    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_2_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
    UR
    1.16
    larından
    1.04
    larının
    1.01
    ו
    0.93
    و
    0.92
    apadani
    0.89
    asına
    0.87
    스로
    0.87
    ERK
    0.87
    ER
    0.86
    POSITIVE LOGITS
     on
    1.77
     or
    1.39
    ت
    1.36
    し
    1.21
    是
    1.15
     reorgan
    1.13
     gun
    1.12
    _
    1.10
    는
    1.10
    は
    1.09
    Activations Density 0.001%

    No Known Activations