© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9954
    Prev
    Next
    INDEX
    Explanations

    few sentences

    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_40_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
    ogenen
    0.44
    тивно
    0.42
    は約
    0.40
     אחת
    0.40
    etrically
    0.39
    婊
    0.38
     pensando
    0.38
    inued
    0.37
    ynos
    0.37
     Luciano
    0.36
    POSITIVE LOGITS
    몇
    1.26
    几
    1.23
     몇
    1.21
     few
    1.18
    few
    1.13
    幾
    1.13
     birkaç
    1.09
     چند
    1.06
    幾個
    1.05
     several
    1.02
    Activations Density 0.222%

    No Known Activations