© 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. 16338
    Prev
    Next
    INDEX
    Explanations

    the phrase "of a" and "an"

    oai_token-act-pair · gemini-2.0-flash

    the word "a"

    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
    <bos>
    -1.20
     
    -0.90
     I
    -0.85
     the
    -0.81
     in
    -0.79
     with
    -0.76
     so
    -0.71
    .
    -0.70
     and
    -0.70
     The
    -0.69
    POSITIVE LOGITS
     Viber
    1.07
     ―――――
    1.07
     disambiguazione
    1.06
     ་་
    1.02
    homonymie
    1.01
    tvguidetime
    0.99
     Keras
    0.98
    InputBorder
    0.96
     photolibrary
    0.96
    WebVitals
    0.96
    Activations Density 0.752%

    No Known Activations