© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64115
    Prev
    Next
    INDEX
    Explanations

    reporting after periods

    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_41_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
    nds
    0.43
     crecimiento
    0.42
     tenths
    0.42
    硞
    0.41
    initis
    0.40
    lingen
    0.38
     accretion
    0.37
     رشد
    0.36
    死亡
    0.36
    成長
    0.36
    POSITIVE LOGITS
     Sources
    0.45
     sources
    0.44
    sources
    0.43
    Sources
    0.43
     reports
    0.38
     हमें
    0.38
     мы
    0.38
     cuánt
    0.38
    ແ
    0.38
     JOIN
    0.38
    Activations Density 0.002%

    No Known Activations