© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 698
    Prev
    Next
    INDEX
    Explanations

    the prefix "ped", especially in the context of medical or criminal terminology

    oai_token-act-pair · gemini-2.0-flash

    ped

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Népesség
    -0.70
    )");
    -0.63
    )";
    -0.62
    bolista
    -0.58
    urbs
    -0.57
     GI
    -0.56
     forKey
    -0.54
    gatsby
    -0.54
     Sinon
    -0.53
    Swatch
    -0.53
    POSITIVE LOGITS
    Vidite
    0.60
     שוליים
    0.60
    تقاوى
    0.57
    хьтан
    0.55
    brechen
    0.51
    衛門
    0.51
    tagHelperRunner
    0.49
     excru
    0.49
    stock
    0.48
    insics
    0.46
    Activations Density 1.119%

    No Known Activations