© 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. 87370
    Prev
    Next
    INDEX
    Explanations

    base64 encoding

    np_max-act-logits · gemini-2.5-flash-lite
    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
     conflict
    0.52
     conflicts
    0.50
     conflic
    0.46
     rub
    0.46
     rs
    0.43
     rubs
    0.41
     ts
    0.41
     conflit
    0.41
     Conflict
    0.40
     ξ
    0.38
    POSITIVE LOGITS
    kl
    0.66
    kn
    0.54
    ki
    0.52
    Mi
    0.50
    ke
    0.49
    gl
    0.49
    nW
    0.48
    kami
    0.48
    nX
    0.48
    Gi
    0.48
    Activations Density 0.001%

    No Known Activations