© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    the phrase "light source"

    oai_token-act-pair · gemini-2.0-flash

    source

    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
     itſelf
    -1.15
     Efq
    -1.13
     themſelves
    -1.10
     becauſe
    -1.05
     uſe
    -1.02
    ^(@)
    -1.02
     himſelf
    -1.01
    drawal
    -1.01
     cauſe
    -1.00
     reaſon
    -1.00
    POSITIVE LOGITS
    o
    0.76
    e
    0.73
    i
    0.69
    en
    0.69
    es
    0.68
    we
    0.67
    res
    0.67
    on
    0.65
    te
    0.65
    for
    0.62
    Activations Density 1.329%

    No Known Activations