© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11271
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with events like conference, gala, ceremony, and lawsuit

    oai_token-act-pair · gemini-2.0-flash

    organized gatherings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    
    -0.59
    ########.
    -0.47
    errHandler
    -0.47
     Mite
    -0.47
    rufe
    -0.44
    ondheim
    -0.44
     Meetings
    -0.43
     COURSES
    -0.42
     zł
    -0.42
    Lur
    -0.42
    POSITIVE LOGITS
     held
    1.01
     оригіналу
    0.86
    held
    0.83
     يتيمه
    0.82
     holding
    0.80
     hold
    0.75
     HELD
    0.75
    holding
    0.72
     <=",
    0.68
     holds
    0.67
    Activations Density 9.995%

    No Known Activations