© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14229
    Prev
    Next
    INDEX
    Explanations

    the word "promotion."

    oai_token-act-pair · gemini-2.0-flash

    promotion

    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
     مشين
    -1.02
     CreateTagHelper
    -0.95
    .}~\
    -0.91
    ousands
    -0.87
    "])
    -0.85
    numerusform
    -0.84
    .~\
    -0.81
     resourceCulture
    -0.81
    "],
    -0.81
     ويكيپ
    -0.80
    POSITIVE LOGITS
    <bos>
    2.19
    ↵↵
    0.87
    '
    0.77
    ↵
    0.77
    a
    0.70
    The
    0.67
    1
    0.67
    is
    0.67
    3
    0.65
    2
    0.64
    Activations Density 1.278%

    No Known Activations