© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143526
    Prev
    Next
    INDEX
    Explanations

    what

    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_46_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
     Each
    0.35
     hamburg
    0.35
     vast
    0.35
    RODUCTION
    0.35
     each
    0.34
    HTTPSampler
    0.34
    ETING
    0.34
     EACH
    0.34
     htt
    0.34
    垀
    0.34
    POSITIVE LOGITS
    成為
    0.50
    problem
    0.47
    Problem
    0.46
     either
    0.45
     problem
    0.43
     Problem
    0.43
    either
    0.43
    成为
    0.43
    Either
    0.42
     problème
    0.41
    Activations Density 0.004%

    No Known Activations