© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32419
    Prev
    Next
    INDEX
    Explanations

    service, data transformation, results

    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_31_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
    عة
    0.36
    <h2>
    0.35
    ©
    0.35
    addGap
    0.34
    Hotel
    0.34
     Kristall
    0.34
    ocean
    0.34
    arikat
    0.33
    decoration
    0.33
     १९
    0.33
    POSITIVE LOGITS
    撇
    0.43
    ,}$
    0.41
    IService
    0.39
     सर्वि
    0.38
     Merrick
    0.38
    晠
    0.38
    欷
    0.38
     Minh
    0.36
     coluna
    0.36
     столб
    0.36
    Activations Density 0.065%

    No Known Activations