© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43861
    Prev
    Next
    INDEX
    Explanations

    achievements, championships, titles, or medals

    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_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
     реє
    0.36
     ຊ
    0.35
    =\{
    0.35
    ພັນ
    0.35
     Okan
    0.35
     رجسٹر
    0.34
     Mount
    0.34
    䧏
    0.34
     Harbor
    0.33
     Lebanese
    0.33
    POSITIVE LOGITS
    anto
    0.35
    ރު
    0.32
    ')
    0.31
     어느
    0.31
     अने
    0.31
    methylsulfanyl
    0.31
    win
    0.30
    ancs
    0.30
    opsis
    0.29
    Application
    0.29
    Activations Density 0.008%

    No Known Activations