© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10664
    Prev
    Next
    INDEX
    Explanations

    positive words like "good" or "bon"

    oai_token-act-pair · gemini-2.0-flash

    bon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ContentAlignment
    -0.61
     ویکی‌پدیا
    -0.50
    jsonwebtoken
    -0.50
    gonic
    -0.48
     remercier
    -0.47
    hline
    -0.46
     τό
    -0.46
    ται
    -0.45
    aol
    -0.44
    rrggbb
    -0.44
    POSITIVE LOGITS
     good
    1.06
    good
    1.05
    GOOD
    0.98
     Good
    0.98
     GOOD
    0.95
    Good
    0.95
     Paglinawan
    0.78
     bad
    0.75
     dobré
    0.72
    calipsis
    0.72
    Activations Density 0.413%

    No Known Activations