© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    the word "mention" or variations of it

    oai_token-act-pair · gemini-2.0-flash

    mention

    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
    Negative Logits
     rense
    -0.66
    ublik
    -0.65
     brazos
    -0.62
     email
    -0.61
    ing
    -0.61
    NECT
    -0.61
    s
    -0.60
    ↵↵
    -0.59
    BRACE
    -0.59
     impacted
    -0.58
    POSITIVE LOGITS
    ⓧ
    0.79
     läßt
    0.77
     idéia
    0.75
     Administrativna
    0.73
     muß
    0.71
    IntoConstraints
    0.69
     Chwiliwch
    0.69
     msec
    0.68
     Assn
    0.67
     isSet
    0.66
    Activations Density 0.893%

    No Known Activations