© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12286
    Prev
    Next
    INDEX
    Explanations

    the word "hell"

    oai_token-act-pair · gemini-2.0-flash

    hell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     hell
    -2.47
     Hell
    -1.84
     heck
    -1.83
    hell
    -1.82
    Hell
    -1.78
     HELL
    -1.70
    HELL
    -1.60
    hells
    -1.09
    heck
    -1.00
     Heck
    -0.98
    POSITIVE LOGITS
     للمعارف
    0.52
    нгредіє
    0.51
    зья
    0.51
    достатки
    0.50
    illem
    0.50
     Observatory
    0.49
    KELEY
    0.48
    φυ
    0.48
    throp
    0.47
    vcut
    0.47
    Activations Density 0.357%

    No Known Activations