© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12626
    Prev
    Next
    INDEX
    Explanations

    the mathematical relationships and equations represented in text

    oai_token-act-pair · gemini-2.0-flash

    terms indicating positive or negative reactions

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

    positive or negative

    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
    DockStyle
    -0.66
     especiais
    -0.65
     odeur
    -0.60
     âgées
    -0.58
     BIBSYS
    -0.58
     quelcon
    -0.57
     florales
    -0.56
     nôtre
    -0.56
     térm
    -0.56
     amitié
    -0.55
    POSITIVE LOGITS
     positive
    0.82
     negative
    0.77
    正
    0.71
     neg
    0.67
    negative
    0.67
     Neg
    0.65
     Positive
    0.65
     posi
    0.65
     Posi
    0.64
    positive
    0.63
    Activations Density 9.168%

    No Known Activations