© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101008
    Prev
    Next
    INDEX
    Explanations

    agents, reflex, observable, encoding

    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
    s
    0.55
    ward
    0.45
    ৰ
    0.45
     diseñ
    0.44
    에
    0.44
    را
    0.44
    ור
    0.44
    으로
    0.43
     ści
    0.43
    AH
    0.43
    POSITIVE LOGITS
     Этот
    0.50
     |”
    0.46
    ောင့်
    0.46
     Ростов
    0.46
    ,..
    0.46
    ..”
    0.46
    јединачна
    0.45
     mumbled
    0.44
     Информация
    0.43
     READING
    0.43
    Activations Density 0.026%

    No Known Activations