© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168145
    Prev
    Next
    INDEX
    Explanations

    . ! ]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     stamped
    0.43
    RET
    0.39
    desired
    0.38
    invoice
    0.37
     piles
    0.37
    𝘥
    0.37
     RET
    0.36
     blobs
    0.36
    med
    0.36
    delim
    0.36
    POSITIVE LOGITS
     screenwriter
    0.44
     लेखक
    0.42
     coaches
    0.39
     Patricia
    0.38
     trener
    0.38
     Commandant
    0.38
    屋
    0.38
     Steve
    0.37
    Patricia
    0.37
     Kenneth
    0.36
    Activations Density 0.000%

    No Known Activations