© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175036
    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_24_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
    unctional
    0.43
     je
    0.39
    $\{
    0.38
    僟
    0.37
     incidence
    0.35
     subsequent
    0.34
    oz
    0.34
     inhib
    0.34
    явить
    0.34
     Incidence
    0.34
    POSITIVE LOGITS
    ଲେ
    0.37
    bursement
    0.36
    )-$
    0.35
    appt
    0.35
    .):
    0.35
    زور
    0.35
     golpe
    0.34
     voul
    0.34
     elet
    0.34
    يرو
    0.34
    Activations Density 0.000%

    No Known Activations