© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233119
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ב
    0.69
    것
    0.68
     anglès
    0.63
    )$:
    0.61
    )$
    0.56
    и
    0.56
     ajout
    0.55
    お
    0.55
    원
    0.55
    "
    0.55
    POSITIVE LOGITS
    as
    0.65
    un
    0.63
    he
    0.63
    an
    0.61
    ala
    0.61
    er
    0.61
    are
    0.56
    el
    0.55
    all
    0.54
    daki
    0.54
    Activations Density 0.000%

    No Known Activations