© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91817
    Prev
    Next
    INDEX
    Explanations

    inner dialogue and doors

    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
    <0x0D>
    0.88
    ও
    0.79
     inner
    0.79
    </h2>
    0.77
    </h3>
    0.75
    j
    0.71
    </b>
    0.70
    ‬
    0.70
    </td>
    0.66
    </i>
    0.66
    POSITIVE LOGITS
     externe
    0.74
     externos
    0.66
    cimientos
    0.65
    dır
    0.62
    ༎
    0.62
    㳚
    0.60
    思路
    0.59
     External
    0.57
     vasena
    0.57
     detalles
    0.57
    Activations Density 0.002%

    No Known Activations