© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    the word "About" or content that would appear in an "About" section, possibly finding descriptions

    oai_token-act-pair · gemini-2.0-flash

    About

    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
     feroit
    -2.05
     avoient
    -1.95
     auroit
    -1.91
     étoient
    -1.81
     enfans
    -1.80
     étoit
    -1.80
     pouvoit
    -1.79
     ainfi
    -1.70
     scolaires
    -1.68
     chré
    -1.66
    POSITIVE LOGITS
     
    1.34
     the
    1.25
     a
    1.09
     “
    1.03
     "
    0.98
      
    0.95
     De
    0.94
    <eos>
    0.92
     ‘
    0.91
     de
    0.91
    Activations Density 1.644%

    No Known Activations