© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196457
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and definitions

    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_27_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
    umbra
    0.35
    Lycodon
    0.33
     nominally
    0.33
    irradiation
    0.33
     slowing
    0.32
    𒊏
    0.32
     vineyards
    0.32
    inputArr
    0.31
     vineyard
    0.31
    କ୍
    0.31
    POSITIVE LOGITS
     Guad
    0.32
     cak
    0.31
    outch
    0.31
     פר
    0.30
     Caffeine
    0.30
    腕
    0.30
     Remo
    0.30
     Appliance
    0.29
     후
    0.29
     पुष्प
    0.29
    Activations Density 0.000%

    No Known Activations