© 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. 162238
    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
    ת
    1.23
    ק
    1.17
    ं
    1.09
    ัง
    1.05
    לה
    1.00
    пи
    0.96
    ю
    0.94
    די
    0.93
    ต์
    0.93
    ม
    0.93
    POSITIVE LOGITS
    <0x0D>
    1.39
    </b>
    1.38
    </strong>
    1.31
     you
    1.28
    you
    1.24
    can
    1.19
    </h4>
    1.16
    9
    1.16
    ve
    1.14
    ámica
    1.13
    Activations Density 0.000%

    No Known Activations