© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16405
    Prev
    Next
    INDEX
    Explanations

    making

    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_15_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
    ดย
    0.23
    ソッド
    0.22
     hé
    0.22
    琭
    0.22
     χρη
    0.21
    小時
    0.21
     служи
    0.21
     xay
    0.21
     wayside
    0.21
     hon
    0.20
    POSITIVE LOGITS
    id
    0.26
    set
    0.25
    हिट
    0.25
     Entfer
    0.24
    how
    0.24
    an
    0.23
    ut
    0.23
    k
    0.23
     üzerine
    0.23
     Evalu
    0.23
    Activations Density 0.308%

    No Known Activations