© 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. 437
    Prev
    Next
    INDEX
    Explanations

    words related to position and construction, especially things at the top or on the outside

    oai_token-act-pair · gemini-2.0-flash

    Locations or parts of things

    np_max-act-logits · 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
     côtés
    -0.69
    Демографія
    -0.59
     parte
    -0.57
     partie
    -0.54
     qualités
    -0.54
     deel
    -0.54
     rigue
    -0.54
     autorités
    -0.53
     partir
    -0.50
     alemanes
    -0.50
    POSITIVE LOGITS
    ſelves
    0.62
     Jefus
    0.62
    rawDesc
    0.62
     Monfieur
    0.60
    ſelf
    0.60
     himſelf
    0.57
     itſelf
    0.57
    felves
    0.57
     themſelves
    0.56
     whoſe
    0.56
    Activations Density 5.827%

    No Known Activations