© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208926
    Prev
    Next
    INDEX
    Explanations

    Ah,

    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_20_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
     Mexican
    0.24
    ança
    0.21
    कृतिक
    0.21
     Other
    0.21
    Otros
    0.21
     Venezuelan
    0.21
     В
    0.20
     inviting
    0.20
    jande
    0.20
     अन्य
    0.20
    POSITIVE LOGITS
    徑
    0.24
    ZIP
    0.24
     radix
    0.23
    OMG
    0.23
     tigris
    0.22
    གྲ
    0.22
    DATE
    0.22
     двигателя
    0.22
    gress
    0.22
     getContentPane
    0.21
    Activations Density 0.000%

    No Known Activations