© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3762
    Prev
    Next
    INDEX
    Explanations

    a variety of short words ending in "se" that have a vowel before the 's', along with random German words

    oai_token-act-pair · gemini-2.0-flash

    loose/loses variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Sandal
    -0.57
    βε
    -0.57
    DockStyle
    -0.56
    úcar
    -0.55
    quedas
    -0.55
    Obrázky
    -0.55
    DataBind
    -0.54
    WEBPACK
    -0.53
    havan
    -0.53
    ographique
    -0.52
    POSITIVE LOGITS
     loose
    0.70
     Loose
    0.68
    Loose
    0.66
    loose
    0.58
     "];
    0.58
     lepas
    0.58
     looser
    0.58
    hassee
    0.57
    וֹת
    0.56
    )”.
    0.56
    Activations Density 1.016%

    No Known Activations