© 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. 81004
    Prev
    Next
    INDEX
    Explanations

    ": "value" pairs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    कॉम
    0.36
     $+\
    0.36
     жи
    0.35
     apothe
    0.35
    জ্জ
    0.35
     গভীরভাবে
    0.34
    breadcrumbs
    0.34
    textfield
    0.33
     GLUT
    0.33
     ап
    0.33
    POSITIVE LOGITS
    裔
    0.38
    結晶
    0.37
    ementara
    0.36
    Willow
    0.36
     vuccanti
    0.35
    ⎠
    0.35
    Merging
    0.35
    Dys
    0.35
    DependentUpon
    0.34
     بقت
    0.34
    Activations Density 0.000%

    No Known Activations