© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16125
    Prev
    Next
    INDEX
    Explanations

    the letter "T" as the first letter of a token in the short document

    oai_token-act-pair · gemini-2.0-flash

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     }}"></
    -0.80
    RunAsync
    -0.67
    BeginContext
    -0.62
    vidad
    -0.60
    ính
    -0.59
    gratis
    -0.57
     ExecuteAsync
    -0.56
    jspb
    -0.56
    itulo
    -0.55
    ostante
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.67
    AYLOR
    0.54
     invokevirtual
    0.54
    
    0.51
    /**
    0.51
    apatalk
    0.50
    se
    0.50
    :✨
    0.50
    endon
    0.49
    Parcelize
    0.48
    Activations Density 1.533%

    No Known Activations