© 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. 232496
    Prev
    Next
    INDEX
    Explanations

    own followed by an article or possessive

    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
    ра
    1.09
    ب
    1.09
    이지만
    1.07
    ку
    1.05
    ي
    0.97
    u
    0.95
    ע
    0.95
    RO
    0.95
    و
    0.94
    ع
    0.93
    POSITIVE LOGITS
    <0x0D>
    1.34
    </h2>
    1.05
    </u>
    1.03
            
    0.99
     perangkat
    0.99
     skewers
    0.94
    </h3>
    0.93
    \
    0.91
     metų
    0.89
    </h6>
    0.89
    Activations Density 0.001%

    No Known Activations