© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155767
    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_60_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
     ὑ
    0.42
     reassure
    0.39
     ఉ
    0.38
     Plum
    0.37
     overpower
    0.37
     Spring
    0.37
     భారతదేశ
    0.37
     indemnify
    0.36
     업
    0.36
     Plumbing
    0.36
    POSITIVE LOGITS
    y
    0.60
    eto
    0.58
    ew
    0.55
    undi
    0.55
    eous
    0.54
    is
    0.54
    yas
    0.53
    amed
    0.52
    ensis
    0.52
    ee
    0.51
    Activations Density 0.000%

    No Known Activations