© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157577
    Prev
    Next
    INDEX
    Explanations

    name parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     রোববার
    0.40
    peicher
    0.38
     кін
    0.37
    mell
    0.37
    蒸
    0.37
    usc
    0.36
     Fell
    0.36
     messageFields
    0.35
     tse
    0.35
    晟
    0.33
    POSITIVE LOGITS
    SLAM
    0.42
    варти
    0.41
    வங்க
    0.40
     Plum
    0.40
     Isid
    0.40
    陸
    0.39
     plum
    0.39
     தொ
    0.39
     Ley
    0.39
    landish
    0.39
    Activations Density 0.000%

    No Known Activations