© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58999
    Prev
    Next
    INDEX
    Explanations

    skill level needed

    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_11_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
     पूर्वक
    0.32
     對
    0.31
     會
    0.30
     Wahr
    0.29
     umož
    0.29
     conceit
    0.29
    cad
    0.28
     kisah
    0.28
     会
    0.28
    就會
    0.28
    POSITIVE LOGITS
    {
    0.34
     {
    0.30
     fillColorSpace
    0.26
    _
    0.26
    ス
    0.26
    CONFIGURATION
    0.25
    <
    0.25
    Sunflower
    0.25
    Nine
    0.25
    SYSTEM
    0.25
    Activations Density 0.004%

    No Known Activations