© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48024
    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_31_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
     originally
    0.38
     निप
    0.38
    มาชิก
    0.38
    टीवी
    0.37
     случи
    0.35
    enzione
    0.33
    PG
    0.32
    之家
    0.32
    ]->
    0.32
    かもし
    0.32
    POSITIVE LOGITS
     Tox
    0.38
     toxin
    0.38
     treten
    0.38
     seawater
    0.36
     XNUMX
    0.36
     fungicide
    0.36
     君
    0.36
     Lift
    0.36
     greatly
    0.36
     Britt
    0.35
    Activations Density 0.000%

    No Known Activations