© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are important or related to scientific or legal documents

    oai_token-act-pair · gemini-2.0-flash

    document excerpts

    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
    Zeneca
    -0.60
    StackNavigator
    -0.56
    بوابة
    -0.52
    ształ
    -0.49
     habet
    -0.48
     démo
    -0.48
     fidélité
    -0.47
     barbati
    -0.47
    sizeCache
    -0.46
     Tyskland
    -0.46
    POSITIVE LOGITS
     o
    2.19
     о
    1.53
     O
    1.52
     ot
    1.31
     ol
    1.26
    O
    1.23
     ο
    1.19
    o
    1.12
     ó
    1.09
     oj
    1.08
    Activations Density 8.583%

    No Known Activations