© 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. 12508
    Prev
    Next
    INDEX
    Explanations

    terminology and abbreviations related to medical research studies and neuroimaging

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "channel."

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

    Medical brain scans

    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
    RenderAtEndOf
    -0.71
    Personensuche
    -0.68
     normaux
    -0.66
    LookAnd
    -0.63
     незавершена
    -0.59
     ISNI
    -0.56
    uxxxx
    -0.56
     russes
    -0.56
     graphiques
    -0.56
     архивлан
    -0.55
    POSITIVE LOGITS
     chan
    0.59
    IntoConstraints
    0.50
    oredCriteria
    0.47
     channel
    0.47
     Chan
    0.46
    rull
    0.46
     Channels
    0.45
    
    0.44
    Chan
    0.44
    channel
    0.43
    Activations Density 3.750%

    No Known Activations