© 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. 161462
    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
    al
    1.54
    ל
    1.25
    ل
    1.17
    。
    1.17
    ।
    1.15
    𝙱
    1.08
    mma
    1.03
    T
    1.03
    ال
    0.98
     cili
    0.98
    POSITIVE LOGITS
    é
    1.13
    ä
    1.12
    ik
    1.09
    м
    1.08
    im
    1.03
    م
    0.97
    ко
    0.96
    </h2>
    0.93
    <0x0D>
    0.91
    un
    0.90
    Activations Density 0.000%

    No Known Activations