© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5859
    Prev
    Next
    INDEX
    Explanations

    words, phrases and numerical values related to physics and electrical engineering

    oai_token-act-pair · gemini-2.0-flash

    Measurement units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     aveug
    -0.84
    uxxxx
    -0.82
     Monfieur
    -0.77
     purpoſe
    -0.76
     enfans
    -0.75
     étrang
    -0.75
     ainfi
    -0.74
     étrangère
    -0.73
     démocr
    -0.73
     mauva
    -0.71
    POSITIVE LOGITS
     per
    0.88
    ,
    0.74
     in
    0.71
    .
    0.69
     for
    0.69
     (
    0.66
     on
    0.64
    !
    0.63
     Per
    0.62
    ;
    0.60
    Activations Density 15.890%

    No Known Activations