© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260830
    Prev
    Next
    INDEX
    Explanations

    URLs including '/'

    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
    padding
    0.18
    ǐ
    0.17
    Programa
    0.17
     बड़ी
    0.17
    saw
    0.17
    ία
    0.17
    ZIE
    0.17
    Weekly
    0.16
    蹦
    0.16
    箜
    0.16
    POSITIVE LOGITS
     fällt
    0.18
     occupe
    0.18
     touches
    0.18
    ahertz
    0.18
     honti
    0.18
     occur
    0.17
     Occup
    0.17
     sont
    0.17
     gegeben
    0.17
     meshes
    0.17
    Activations Density 0.001%

    No Known Activations