© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words and phrases related to technology, coding, medicine, legal arguments and academia

    oai_token-act-pair · gemini-2.0-flash

    plural nouns

    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
     الرياضيه
    -0.59
     Efq
    -0.52
     Portail
    -0.48
     Profitez
    -0.48
     Inscrivez
    -0.47
     Eſ
    -0.46
     purpoſe
    -0.45
     ModelExpression
    -0.44
     Abonnez
    -0.43
     Vainqueur
    -0.43
    POSITIVE LOGITS
     Cars
    0.92
     Companies
    0.91
     Cities
    0.89
     Teams
    0.88
     Groups
    0.88
     Stocks
    0.87
    Groups
    0.86
     Trains
    0.86
     Plants
    0.85
     Places
    0.85
    Activations Density 13.023%

    No Known Activations