© 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. 167924
    Prev
    Next
    INDEX
    Explanations

    variable names bc and xy

    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
     cascades
    0.40
     Phase
    0.38
    马
    0.38
     CASCADE
    0.37
    馬
    0.37
     PHASE
    0.36
    itect
    0.36
     Melrose
    0.36
    htaking
    0.36
    ారణ
    0.36
    POSITIVE LOGITS
     individuales
    0.37
    மதி
    0.37
    Castro
    0.36
     evaluaciones
    0.36
    Neil
    0.35
    存
    0.34
    それぞれ
    0.34
     Moi
    0.34
    𒃶
    0.34
     regarder
    0.33
    Activations Density 0.000%

    No Known Activations