© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 58720
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    /**
    0.40
    =$\
    0.40
    ldots
    0.38
    ትክል
    0.37
    …,
    0.37
     Архивная
    0.36
     **)
    0.35
    -$\
    0.34
    ﮏ
    0.34
    /**',
    0.33
    POSITIVE LOGITS
    </b>
    2.05
    </strong>
    2.03
    </i>
    2.03
    </em>
    2.02
    </code>
    1.99
    </u>
    1.91
    </sub>
    1.70
    ‬
    1.62
    </span>
    1.59
    </s>
    1.48
    Activations Density 0.244%

    No Known Activations