© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13923
    Prev
    Next
    INDEX
    Explanations

    mentions of funding, awards, and institutes related to medical research

    oai_token-act-pair · gemini-2.0-flash

    Research papers

    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
    URLException
    -0.65
     архивлан
    -0.56
    licitud
    -0.55
     Lordships
    -0.55
    ArgsConstructor
    -0.54
    ☸
    -0.53
    glades
    -0.52
     continuant
    -0.51
    ergies
    -0.50
     Trin
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.79
    tagHelperRunner
    0.72
    findpost
    0.66
     disambiguazione
    0.65
     surla
    0.59
     متعلقه
    0.59
    
    0.58
    SequentialGroup
    0.54
    PyExc
    0.53
    ','$
    0.50
    Activations Density 4.175%

    No Known Activations