© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136290
    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_12_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
    üsseldorf
    0.63
    lø
    0.57
    TL
    0.53
    .<
    0.53
    ichting
    0.52
    jakarta
    0.52
    laşt
    0.49
     பாதிக்கிறது
    0.49
    𝓵
    0.49
     ብዙውን
    0.49
    POSITIVE LOGITS
    '
    0.61
     those
    0.57
     những
    0.56
     valv
    0.55
     no
    0.53
     do
    0.53
     theoretical
    0.53
     thrombo
    0.52
     so
    0.51
     consequences
    0.51
    Activations Density 0.000%

    No Known Activations