© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 650
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    GraphicsUnit
    -0.70
    Demikian
    -0.69
    Portale
    -0.69
    matchCondition
    -0.66
    findpost
    -0.60
    +#+#
    -0.60
    (©
    -0.57
     pinulongan
    -0.56
     Wicidata
    -0.56
    devamını
    -0.56
    POSITIVE LOGITS
    utilité
    0.58
     Lucinda
    0.54
     Yvette
    0.49
     fédé
    0.48
     dör
    0.47
    uatan
    0.47
    ướ
    0.46
     Melanie
    0.45
     Romance
    0.45
    Jeez
    0.45
    Activations Density 8.963%

    No Known Activations