© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11007
    Prev
    Next
    INDEX
    Explanations

    the word "English"

    oai_token-act-pair · gemini-2.0-flash

    English

    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
     Once
    -0.63
    Colle
    -0.63
    Once
    -0.62
     faſt
    -0.62
     Colle
    -0.61
     cale
    -0.61
    λές
    -0.60
     Diſ
    -0.59
     Infin
    -0.58
    engesch
    -0.58
    POSITIVE LOGITS
     चीज़ों
    0.76
    OGND
    0.76
    ⓧ
    0.75
    addCriterion
    0.75
     ComVisible
    0.71
     répondit
    0.70
    "]/
    0.66
    invokeLater
    0.65
    ChildScrollView
    0.65
    ")));
    0.64
    Activations Density 1.677%

    No Known Activations