© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5789
    Prev
    Next
    INDEX
    Explanations

    a mix of foreign language fragments, typos or badly transcribed text, and a few English words about powering and helping.

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    usermodel
    -0.62
    ellation
    -0.56
     bodyParser
    -0.55
    TextWatcher
    -0.55
    hawa
    -0.54
    (",");
    -0.53
    scry
    -0.52
     sko
    -0.52
    nement
    -0.52
    …~
    -0.51
    POSITIVE LOGITS
    <bos>
    1.55
     behind
    1.19
    behind
    1.14
    Behind
    1.13
     Behind
    1.05
     BEHIND
    0.95
     trás
    0.94
     dietro
    0.90
     detrás
    0.88
     derrière
    0.86
    Activations Density 0.313%

    No Known Activations