© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9113
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially locations and organizations

    oai_token-act-pair · gemini-2.0-flash

    Natural features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ſelves
    -0.68
    Rüyada
    -0.65
     Efq
    -0.65
    maiden
    -0.63
     ImportError
    -0.63
     تانيه
    -0.61
     myſelf
    -0.61
     мәкал
    -0.61
     preſent
    -0.61
     yoox
    -0.61
    POSITIVE LOGITS
     Sta
    0.58
    Sta
    0.49
     bridge
    0.48
     en
    0.47
     Bridge
    0.46
     sta
    0.46
    橋
    0.45
     D
    0.44
    bürgermeister
    0.44
     World
    0.44
    Activations Density 1.117%

    No Known Activations