© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    the keyword "pub" in code snippets

    oai_token-act-pair · gemini-2.0-flash

    pub

    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
     Monfieur
    -1.24
     Cæsar
    -1.16
     Diſ
    -1.13
     ſeveral
    -1.11
     Reſ
    -1.10
     ―――――
    -1.09
     Theſe
    -1.08
     ainfi
    -1.06
     étoient
    -1.05
     houſe
    -1.05
    POSITIVE LOGITS
     qu
    0.76
     
    0.74
     my
    0.73
     in
    0.70
     so
    0.70
     plus
    0.70
     non
    0.67
     var
    0.65
     this
    0.65
     (
    0.65
    Activations Density 1.642%

    No Known Activations