© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 5949
    Prev
    Next
    INDEX
    Explanations

    the word "publicly"

    oai_token-act-pair · gemini-2.0-flash

    publicly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -1.14
     and
    -0.99
     (
    -0.86
     of
    -0.79
    -
    -0.77
     or
    -0.77
     
    -0.76
     a
    -0.74
     in
    -0.74
     –
    -0.73
    POSITIVE LOGITS
     Efq
    1.63
     Monfieur
    1.59
     ainfi
    1.56
     Theſe
    1.48
     avoient
    1.47
     becauſe
    1.43
     ſeveral
    1.43
     étoit
    1.43
     feroit
    1.42
     auffi
    1.41
    Activations Density 3.385%

    No Known Activations