© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46488
    Prev
    Next
    INDEX
    Explanations

    emulator and simulator

    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_22_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
    ామని
    0.42
     Nullam
    0.42
    pect
    0.40
     নাকি
    0.40
    くなる
    0.40
    codingPath
    0.40
     div
    0.39
    priv
    0.38
    噌
    0.38
    もち
    0.38
    POSITIVE LOGITS
     Gl
    0.43
     conquer
    0.42
     transcribe
    0.42
    Gl
    0.40
     silence
    0.40
     AVEN
    0.40
     excursions
    0.39
    uco
    0.39
     others
    0.39
     tracing
    0.39
    Activations Density 0.000%

    No Known Activations