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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4486
    Prev
    Next
    INDEX
    Explanations

    words related to health, measurements, and body composition

    oai_token-act-pair · gemini-2.0-flash

    terms related to energy and weight

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

    body weight/fat/obesity

    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
    SequentialGroup
    -0.62
     محفوظة
    -0.53
    ieza
    -0.53
    帖最后由
    -0.52
    miyorum
    -0.52
    ilibrium
    -0.51
    lloworld
    -0.50
    intellij
    -0.50
    balleur
    -0.49
     konu
    -0.47
    POSITIVE LOGITS
    expandindo
    0.58
     energy
    0.56
     bağlantılar
    0.55
    contentLoaded
    0.54
     weight
    0.53
     resourceCulture
    0.53
     estekak
    0.52
    GEBURTSDATUM
    0.51
     Energy
    0.50
    Energy
    0.49
    Activations Density 3.737%

    No Known Activations