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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52834
    Prev
    Next
    INDEX
    Explanations

    sequential image numbering

    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
     dov
    0.33
     directory
    0.32
    卧
    0.32
    表記
    0.32
     planche
    0.32
     hourglass
    0.31
     প্রেমের
    0.31
     directorio
    0.31
     প্রেম
    0.31
     thoughts
    0.30
    POSITIVE LOGITS
    expensive
    0.37
    testing
    0.33
    UKI
    0.32
    after
    0.31
    찍
    0.31
     photographers
    0.31
    鿢
    0.31
    Destroy
    0.30
     বিটিআই
    0.30
     laboratories
    0.30
    Activations Density 0.001%

    No Known Activations