© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14665
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols and equations.

    oai_token-act-pair · gemini-2.0-flash

    Bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Personendaten
    -1.55
    GEBURTSDATUM
    -1.38
     propOrder
    -1.23
    
    -1.23
    PreferredItem
    -1.22
     мәкал
    -1.16
    InjectAttribute
    -1.16
    writeFieldEnd
    -1.13
    StoryboardSegue
    -1.11
    AndEndTag
    -1.10
    POSITIVE LOGITS
    adecimal
    0.42
    arithmic
    0.41
    nenie
    0.41
    getBase
    0.40
     تانيه
    0.40
    kranz
    0.40
    roughts
    0.39
    InBytes
    0.39
     first
    0.39
     Atti
    0.38
    Activations Density 17.601%

    No Known Activations