© 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. 2319
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers and code-like elements, possibly representing data tables or programming syntax

    oai_token-act-pair · gemini-2.0-flash

    identifiers

    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
    itch
    -0.51
     مُعرِّف
    -0.50
    rean
    -0.50
    yin
    -0.48
     Morris
    -0.47
    eas
    -0.47
     boa
    -0.47
     Fisch
    -0.47
     Cham
    -0.46
    champ
    -0.46
    POSITIVE LOGITS
    헌
    0.62
     defStyleAttr
    0.62
     XNUMX
    0.60
     Stefani
    0.60
     defStyle
    0.59
     tetanus
    0.59
     Cune
    0.59
     Rosenberg
    0.59
     Assignee
    0.59
     Cey
    0.59
    Activations Density 4.839%

    No Known Activations