© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247245
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis)

    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_40_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
    旷
    0.42
    embre
    0.41
    ilust
    0.40
     Ether
    0.38
     Pie
    0.37
     Singapore
    0.37
     pi
    0.37
     रिली
    0.37
     Blair
    0.36
    𝜋
    0.36
    POSITIVE LOGITS
    狞
    0.39
     darkened
    0.38
     descends
    0.37
    Common
    0.37
     descended
    0.37
    ekwondo
    0.36
     UConn
    0.35
    ान्य
    0.35
     ดวง
    0.35
    scaled
    0.34
    Activations Density 0.002%

    No Known Activations