© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16220
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to commercial products.

    oai_token-act-pair · gemini-2.0-flash

    features or functionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Autoritní
    -0.74
    +#+#
    -0.69
    
    -0.63
    kuuta
    -0.63
    RectangleBorder
    -0.63
     Lij
    -0.61
    جوايز
    -0.60
    endphp
    -0.59
    ynchrotron
    -0.59
    gettyimages
    -0.58
    POSITIVE LOGITS
     WebDriverWait
    0.50
     Exacts
    0.45
     PARSER
    0.44
     Yes
    0.42
    AsUp
    0.41
    InjectAttribute
    0.41
     writeTo
    0.41
    여
    0.41
    Yes
    0.40
    ểu
    0.39
    Activations Density 22.841%

    No Known Activations