© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209134
    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_56_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
     separate
    0.46
     Separate
    0.43
    Separate
    0.43
     отде
    0.42
    separate
    0.41
     related
    0.40
     별
    0.39
    வதால்
    0.39
     officer
    0.38
     Int
    0.38
    POSITIVE LOGITS
     fact
    0.55
     magnitude
    0.42
     Probe
    0.42
     fakt
    0.41
    fact
    0.41
    ʿ
    0.40
    Magnitude
    0.39
     probes
    0.39
     Magnitude
    0.39
     фак
    0.38
    Activations Density 0.000%

    No Known Activations