© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10197
    Prev
    Next
    INDEX
    Explanations

    reserved words in code and code syntax elements

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     szív
    -0.43
     coraggio
    -0.41
     edifício
    -0.38
     nyug
    -0.37
     tayang
    -0.37
    forsch
    -0.36
    acağına
    -0.35
    faster
    -0.35
     castelo
    -0.34
    HIND
    -0.34
    POSITIVE LOGITS
     propOrder
    0.82
    Jereo
    0.81
    extAlignment
    0.81
     Италијани
    0.79
    featureID
    0.75
     препратки
    0.72
     EClass
    0.70
     الرياضيه
    0.69
     يتيمه
    0.69
    Personensuche
    0.68
    Activations Density 11.311%

    No Known Activations