© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15840
    Prev
    Next
    INDEX
    Explanations

    various numbers and digits

    oai_token-act-pair · gemini-2.0-flash

    Number six

    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
    oredCriteria
    -1.02
     nahilalakip
    -0.77
    ThroughAttribute
    -0.77
    ⓧ
    -0.72
    contentLoaded
    -0.71
    makeConstraints
    -0.70
     Autorizaciones
    -0.69
     fifteenth
    -0.69
    #![
    -0.65
    EDEFAULT
    -0.64
    POSITIVE LOGITS
    6
    1.52
     six
    1.20
     Six
    1.19
     Sixty
    1.05
    ６
    1.03
     SIX
    1.02
    六
    1.00
     sixty
    0.99
     sixth
    0.97
    Six
    0.96
    Activations Density 2.407%

    No Known Activations