© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232777
    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_6_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
    .
    1.13
     sanit
    1.01
    이다
    1.00
     spectrum
    1.00
    లు
    0.96
     rasgos
    0.96
    ل
    0.95
     wave
    0.93
     trocar
    0.93
     passivation
    0.92
    POSITIVE LOGITS
    x
    1.25
    ق
    1.22
     In
    1.18
     It
    1.14
     There
    1.11
     If
    1.08
     Orang
    1.05
    k
    1.05
     This
    1.05
    ta
    1.05
    Activations Density 0.000%

    No Known Activations