© 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. 161397
    Prev
    Next
    INDEX
    Explanations

    hold or held

    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
     Dand
    0.40
     takeover
    0.40
     Daisy
    0.39
     suspension
    0.38
    ediat
    0.37
     rigorously
    0.36
     LONDON
    0.35
    Laptop
    0.34
    딘
    0.34
    inset
    0.34
    POSITIVE LOGITS
     regenv
    0.38
     லா
    0.37
    被人
    0.35
    輋
    0.35
     বুলেট
    0.34
     cárc
    0.34
     থান
    0.33
    killed
    0.33
     accused
    0.32
     treas
    0.32
    Activations Density 0.005%

    No Known Activations