© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    require statements

    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
    యితే
    0.27
     AsRef
    0.26
    簀
    0.26
    AGMENT
    0.25
    rement
    0.25
     synthetic
    0.25
    synthetic
    0.25
     |_{
    0.25
     Pry
    0.25
     IntPtr
    0.25
    POSITIVE LOGITS
    Cla
    0.31
    Cabe
    0.28
    IPV
    0.27
     Cla
    0.26
    Univers
    0.26
     म्ह
    0.25
    Spe
    0.25
    Cape
    0.25
    CLA
    0.25
     Cape
    0.24
    Activations Density 0.005%

    No Known Activations