© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99622
    Prev
    Next
    INDEX
    Explanations

    route files

    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_14_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
     dobře
    0.46
    始めた
    0.46
    Fishing
    0.45
    Put
    0.45
    лав
    0.45
     genotyping
    0.44
    FOX
    0.43
    Ｆ
    0.43
    LOG
    0.43
    高志森
    0.42
    POSITIVE LOGITS
    ol
    0.53
    ravariant
    0.52
    udian
    0.50
    redos
    0.50
     ellos
    0.49
    algam
    0.49
    ose
    0.49
    qs
    0.49
     zwr
    0.48
     मुगल
    0.48
    Activations Density 0.000%

    No Known Activations