© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134624
    Prev
    Next
    INDEX
    Explanations

    VK7JG-NPHTM-C97JM-9MPGT-3V66T

    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_6_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
     as
    1.11
    ส
    0.99
     os
    0.97
     this
    0.96
     el
    0.89
     analogy
    0.88
    し
    0.86
     jud
    0.86
     ash
    0.86
    습니다
    0.85
    POSITIVE LOGITS
    x
    1.22
    دين
    0.98
    Y
    0.98
    ﺭ
    0.94
    U
    0.92
    А
    0.92
    ಯ
    0.91
    Т
    0.89
    of
    0.89
    на
    0.88
    Activations Density 0.000%

    No Known Activations