© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9929
    Prev
    Next
    INDEX
    Explanations

    the word "chairman" in the context of describing a person's history

    oai_token-act-pair · gemini-2.0-flash

    governance and politics

    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
    tvguidetime
    -0.69
    enumi
    -0.68
    oredCriteria
    -0.65
    webElementGuid
    -0.64
     برانيه
    -0.64
     []:
    -0.63
    الإنجليزية
    -0.61
     EconPapers
    -0.61
    CloseOperation
    -0.61
     saites
    -0.61
    POSITIVE LOGITS
     tribun
    0.47
     scio
    0.47
     aDecoder
    0.47
    ταν
    0.47
    رشف
    0.47
    undang
    0.46
    ArrowToggle
    0.45
    (',');
    0.45
    WebServlet
    0.44
    Sain
    0.43
    Activations Density 4.024%

    No Known Activations