© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134210
    Prev
    Next
    INDEX
    Explanations

    peace and love

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ald
    0.46
    otri
    0.42
    </tr>
    0.39
    杓
    0.38
     hObject
    0.37
     Stunde
    0.37
    วิ่ง
    0.37
     rail
    0.37
    razi
    0.37
     Hours
    0.36
    POSITIVE LOGITS
    sohn
    0.47
     Peel
    0.43
    Soul
    0.41
    Graham
    0.41
    mason
    0.40
    墨
    0.40
    ulu
    0.40
    venus
    0.40
    ノート
    0.38
    exon
    0.38
    Activations Density 0.008%

    No Known Activations