© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13064
    Prev
    Next
    INDEX
    Explanations

    verbs related to observation and expression (especially facial)

    oai_token-act-pair · gemini-2.0-flash

    sight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ($__
    -0.64
    batore
    -0.63
     OFDb
    -0.63
     незавершена
    -0.62
     يتيمه
    -0.58
    łgor
    -0.57
     <>",
    -0.57
     AssemblyCulture
    -0.57
     تضيفلها
    -0.56
    fjspx
    -0.56
    POSITIVE LOGITS
     comput
    0.53
    동
    0.50
    Profile
    0.50
     Tread
    0.49
     qu
    0.49
    difer
    0.48
     paral
    0.47
     Opportun
    0.47
    ilung
    0.47
    vac
    0.47
    Activations Density 2.063%

    No Known Activations