© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13102
    Prev
    Next
    INDEX
    Explanations

    words associated with people with strong interests who enjoy something

    oai_token-act-pair · gemini-2.0-flash

    love

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    newtheorem
    -0.54
    Geplaatst
    -0.51
    OGND
    -0.50
    Naissance
    -0.49
    umpad
    -0.48
    NOPQRST
    -0.48
    RuleContext
    -0.47
    riturismo
    -0.46
    IContainer
    -0.45
    http
    -0.44
    POSITIVE LOGITS
     love
    0.78
     loves
    0.71
     LOVE
    0.64
     liebt
    0.63
    love
    0.62
     adore
    0.62
    Atentamente
    0.61
    XmlAccessType
    0.59
     loved
    0.59
    loves
    0.59
    Activations Density 0.662%

    No Known Activations