© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 234285
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     eight
    0.45
     ஏழு
    0.45
     six
    0.44
     seven
    0.44
     Six
    0.43
     nine
    0.42
     four
    0.40
     ۲
    0.40
     आठ
    0.40
     ٣
    0.40
    POSITIVE LOGITS
     banner
    0.41
     以下
    0.40
    下方
    0.38
    ቑ
    0.38
     bootstrap
    0.37
     सटी
    0.36
     Katt
    0.36
     backcountry
    0.36
    Sak
    0.36
     fontes
    0.36
    Activations Density 0.006%

    No Known Activations