© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13192
    Prev
    Next
    INDEX
    Explanations

    the acronym "ERT" as well as HTML unicode

    oai_token-act-pair · gemini-2.0-flash

    ERT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    новништво
    -0.61
    })));
    -0.59
    下载附件
    -0.58
    }$​
    -0.58
    //
    -0.57
    ungkin
    -0.57
    født
    -0.56
     propOrder
    -0.55
    tli
    -0.55
    Referanser
    -0.55
    POSITIVE LOGITS
    ter
    0.95
    ters
    0.88
    TER
    0.85
    eter
    0.77
    ater
    0.77
     ter
    0.76
    тер
    0.73
    Ter
    0.71
    nter
    0.69
    teri
    0.69
    Activations Density 0.266%

    No Known Activations