© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ك
    1.76
    ع
    1.58
    ون
    1.30
    ک
    1.30
    un
    1.29
    ل
    1.27
     is
    1.23
    ته
    1.20
    ي
    1.17
    ра
    1.13
    POSITIVE LOGITS
    9
    1.33
    n
    1.22
    8
    1.03
    nél
    0.98
    否
    0.94
    /
    0.91
     conflic
    0.90
     trifling
    0.90
    7
    0.90
    naires
    0.88
    Activations Density 0.000%

    No Known Activations