© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1930
    Prev
    Next
    INDEX
    Explanations

    words that start with "re" or indicate the state of something being changed

    oai_token-act-pair · gemini-2.0-flash

    prefixes re and out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tivation
    -0.62
     Devotion
    -0.58
     adoption
    -0.57
    Provider
    -0.57
     assessment
    -0.54
     Biv
    -0.54
     connection
    -0.53
     trade
    -0.52
    lication
    -0.52
     Det
    -0.52
    POSITIVE LOGITS
    headed
    0.54
    gotta
    0.54
     nôtre
    0.50
    grown
    0.50
    MENAFN
    0.50
    troppo
    0.49
    driven
    0.48
     tantôt
    0.48
     Regno
    0.47
     tarko
    0.47
    Activations Density 2.741%

    No Known Activations