© 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. 201224
    Prev
    Next
    INDEX
    Explanations

    bab

    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
     targeting
    0.41
    сси
    0.40
     Targeting
    0.40
    දී
    0.39
     चौराहे
    0.37
    ચ
    0.37
    tgt
    0.37
    redirectTo
    0.37
    STEN
    0.36
     самих
    0.36
    POSITIVE LOGITS
    illos
    0.44
     dock
    0.37
     производстве
    0.35
    <thead>
    0.35
    𒆪
    0.35
     admisión
    0.34
    ্যো
    0.34
    柩
    0.34
    illera
    0.34
     Prag
    0.34
    Activations Density 0.000%

    No Known Activations