© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with someone speaking or being quoted about scientific studies.

    oai_token-act-pair · gemini-2.0-flash

    Names and quotations

    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
     Roskov
    -0.75
     propOrder
    -0.71
     Италијани
    -0.71
     Normdatei
    -0.68
    TintMode
    -0.59
    aarrggbb
    -0.57
     kaarangay
    -0.56
    oredCriteria
    -0.56
    soort
    -0.55
    sidemargin
    -0.55
    POSITIVE LOGITS
     Irina
    0.65
     Silvio
    0.65
     Rajiv
    0.62
    ABU
    0.61
     mariana
    0.60
     Mariana
    0.60
     Sandro
    0.59
     ISE
    0.59
     Hui
    0.59
     IFC
    0.59
    Activations Density 10.085%

    No Known Activations