© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87679
    Prev
    Next
    INDEX
    Explanations

    a direct address to "you"

    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
    ↵
    0.99
    </h3>
    0.79
    </li>
    0.66
    On
    0.64
     Charities
    0.64
    </h2>
    0.63
    ink
    0.63
    </td>
    0.62
    ్
    0.62
    ro
    0.61
    POSITIVE LOGITS
    ن
    1.16
    न
    1.04
    ন
    1.04
    ری
    1.03
    น
    1.02
    ン
    1.02
    ش
    0.94
    기
    0.91
    ва
    0.89
    у
    0.84
    Activations Density 0.014%

    No Known Activations