© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260754
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     "
    0.52
    '.
    0.50
    session
    0.50
     session
    0.49
    .
    0.47
    pler
    0.47
     sister
    0.47
     to
    0.46
     so
    0.46
     there
    0.45
    POSITIVE LOGITS
     Góc
    0.57
    expandindo
    0.53
     ваш
    0.51
    สวย
    0.49
    角落
    0.49
    currentCharacter
    0.47
     Especific
    0.47
    >|</
    0.47
     вашу
    0.47
    フグ
    0.46
    Activations Density 0.000%

    No Known Activations