© 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. 58366
    Prev
    Next
    INDEX
    Explanations

    DOW JONES

    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_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
     to
    1.38
    0
    1.23
    <0x0D>
    1.20
    </h2>
    1.17
    s
    1.15
    ب
    1.13
    </td>
    1.12
    </strong>
    1.11
    </code>
    1.11
    ט
    1.09
    POSITIVE LOGITS
    el
    1.40
    in
    1.37
    as
    1.23
     décerné
    1.23
    ed
    1.21
    әк
    1.18
    ﺖ
    1.15
    pping
    1.11
    риев
    1.09
     réduit
    1.09
    Activations Density 0.000%

    No Known Activations