© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4604
    Prev
    Next
    INDEX
    Explanations

    history.com topics

    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_39_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
     accelerate
    0.39
     bis
    0.37
    циями
    0.36
     accelerates
    0.36
    achy
    0.35
     execute
    0.35
     Traverse
    0.35
    ][
    0.34
    acceler
    0.34
     exped
    0.34
    POSITIVE LOGITS
     profilo
    0.42
     SOCIETY
    0.38
     feminism
    0.38
     Wetlands
    0.38
    BACKGROUND
    0.38
     BACKGROUND
    0.38
     plaque
    0.37
    綱
    0.37
    Contemporary
    0.37
    olyb
    0.36
    Activations Density 0.002%

    No Known Activations