© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104622
    Prev
    Next
    INDEX
    Explanations

    real-world implications

    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_1_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
    </b>
    1.47
    ↵↵
    1.39
    </i>
    1.38
    </h2>
    1.24
    </h3>
    1.24
    ↵
    1.22
    ‬
    1.16
    া
    1.15
    </u>
    1.13
    ↵↵↵
    1.07
    POSITIVE LOGITS
    of
    1.40
    are
    1.08
    ق
    1.05
    ку
    1.00
    ش
    0.97
    اء
    0.95
    varchar
    0.94
     EBITDA
    0.94
    iii
    0.93
    ج
    0.93
    Activations Density 0.005%

    No Known Activations