© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9775
    Prev
    Next
    INDEX
    Explanations

    text related to health, safety and avoiding danger.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and actions

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     تانيه
    -0.61
    aktur
    -0.52
     Redmi
    -0.50
     Désolé
    -0.48
     laude
    -0.48
    üks
    -0.47
     estimés
    -0.47
     grego
    -0.47
     authorship
    -0.45
    otesi
    -0.45
    POSITIVE LOGITS
     follow
    0.76
    StructEnd
    0.73
     kasarigan
    0.72
     Follow
    0.69
    رشف
    0.68
     getItemId
    0.64
     try
    0.64
    follow
    0.63
    MLLoader
    0.59
     remove
    0.58
    Activations Density 3.353%

    No Known Activations