© 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. 5165
    Prev
    Next
    INDEX
    Explanations

    words related to company information, sectors, and news

    oai_token-act-pair · gemini-2.0-flash

    News and publications

    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
    FormState
    -0.56
    picasso
    -0.49
    WebServlet
    -0.48
    élie
    -0.47
    ίος
    -0.47
    "]}
    -0.46
    êng
    -0.45
    crollView
    -0.44
    Datuak
    -0.43
    FormData
    -0.43
    POSITIVE LOGITS
     "..\..\
    0.65
     EconPapers
    0.63
    offsetof
    0.62
    astéroïdes
    0.56
    unknownFields
    0.55
     "..\..\..\
    0.54
    iconque
    0.54
     internetowa
    0.52
     '\\;'
    0.50
     autorytatywna
    0.50
    Activations Density 8.177%

    No Known Activations