© 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. 112571
    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
    א
    0.84
    ש
    0.75
    ি
    0.63
    ethe
    0.61
    (.*
    0.59
    다
    0.59
    ים
    0.59
    ே
    0.58
    dır
    0.57
    یی
    0.56
    POSITIVE LOGITS
    ف
    0.80
    أ
    0.77
    </h3>
    0.75
    不
    0.75
    ER
    0.74
    要
    0.73
    ض
    0.70
    ne
    0.66
    沒有
    0.66
    U
    0.65
    Activations Density 0.000%

    No Known Activations