© 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. 9458
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "quickly" and sometimes also numbers or common words like "both", "own", "you" or "mobile"

    oai_token-act-pair · gemini-2.0-flash

    quickly

    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
     étoient
    -1.53
     avoient
    -1.52
     enfans
    -1.46
     auroit
    -1.45
     étoit
    -1.37
     religieuses
    -1.32
     pouvoit
    -1.25
     feroit
    -1.24
     chré
    -1.23
     ainfi
    -1.20
    POSITIVE LOGITS
     ExecuteAsync
    0.92
    ]));
    0.90
    fillType
    0.86
     CreateTagHelper
    0.84
    UpInside
    0.83
    ⓧ
    0.83
    EndProject
    0.81
     JpaRepository
    0.80
     مشين
    0.79
     Paglinawan
    0.79
    Activations Density 2.290%

    No Known Activations