© 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. 6050
    Prev
    Next
    INDEX
    Explanations

    words from internet chat relating to software or location, combined with polite conversational phrases

    oai_token-act-pair · gemini-2.0-flash

    IRC and code snippets

    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
     !
    -2.20
     :
    -2.06
     ;
    -2.00
     ?
    -1.91
     !”
    -1.71
     !"
    -1.64
     !!
    -1.60
     !)
    -1.60
     ?"
    -1.58
     ?”
    -1.54
    POSITIVE LOGITS
    </caption>
    0.69
    IntoConstraints
    0.67
     ―――――
    0.63
    
    0.62
    Datuak
    0.60
     }}$}
    0.59
     Перейти
    0.58
    zungen
    0.56
     вікі
    0.56
     Theſe
    0.56
    Activations Density 4.192%

    No Known Activations