© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41630
    Prev
    Next
    INDEX
    Explanations

    RoBERTa

    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_3_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
    d
    0.88
    </h2>
    0.86
    ↵
    0.82
    <0x0D>
    0.75
    </h3>
    0.73
    ↵↵
    0.73
    </b>
    0.72
    dg
    0.70
    </th>
    0.66
    ך
    0.66
    POSITIVE LOGITS
    ية
    1.13
    ва
    0.89
    يف
    0.85
    రణ
    0.83
    يت
    0.79
    隀
    0.79
    إن
    0.77
    ادة
    0.77
    يدة
    0.77
     by
    0.76
    Activations Density 0.001%

    No Known Activations