© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99408
    Prev
    Next
    INDEX
    Explanations

    key explanation

    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_14_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
    äk
    0.32
    к
    0.30
     mesmos
    0.29
     mismo
    0.29
     একই
    0.29
    udev
    0.28
     communs
    0.27
     stessi
    0.27
     claros
    0.27
    कल
    0.26
    POSITIVE LOGITS
     ដោយ
    0.33
     他
    0.31
     በፊት
    0.31
     tenant
    0.31
    হইতে
    0.31
    Blade
    0.30
     noodle
    0.30
     ただ
    0.30
    tenant
    0.30
     Asphalt
    0.29
    Activations Density 0.018%

    No Known Activations