© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 151741
    Prev
    Next
    INDEX
    Explanations

    important point

    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_23_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
     depolarization
    0.41
     contained
    0.37
     encirc
    0.37
     today
    0.36
     આજ
    0.36
     depository
    0.36
     depolar
    0.36
    ዙ
    0.36
    اهلا
    0.35
    स्वागत
    0.35
    POSITIVE LOGITS
     encomenda
    0.35
     процесса
    0.35
    èves
    0.34
    icel
    0.32
     MAH
    0.32
    gebras
    0.31
    ımız
    0.31
    nitz
    0.31
     MAM
    0.31
    nière
    0.31
    Activations Density 0.003%

    No Known Activations