© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6832
    Prev
    Next
    INDEX
    Explanations

    named entities and locations of specific events mostly related to the Canadian government

    oai_token-act-pair · gemini-2.0-flash

    coding terms or technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    Canadian or Canada

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    참고
    -0.60
    FailureListener
    -0.53
    
    -0.52
    Referanser
    -0.48
     상세
    -0.48
     SEC
    -0.48
     vicepresidente
    -0.47
    Referințe
    -0.46
     PRESIDENT
    -0.46
     EdgeInsets
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.65
    interopRequire
    0.65
    AndEndTag
    0.58
    AddHtmlAttribute
    0.56
     esto
    0.56
     rø
    0.56
    gien
    0.55
    ξεις
    0.55
    зулта
    0.55
    phat
    0.55
    Activations Density 0.533%

    No Known Activations