© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33952
    Prev
    Next
    INDEX
    Explanations

    Salmon

    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
     Alford
    0.43
     Lithium
    0.39
     eryth
    0.38
     ngư
    0.38
    锂
    0.38
    PhoneNumber
    0.38
     Audiodateien
    0.38
     ओलंप
    0.37
    鋰
    0.37
    igungs
    0.37
    POSITIVE LOGITS
    elle
    2.03
    Elle
    1.85
    ELLE
    1.84
     Elle
    1.84
    Ella
    1.81
     Ella
    1.80
     elle
    1.77
    ella
    1.73
    elles
    1.64
     ella
    1.62
    Activations Density 0.001%

    No Known Activations