© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10987
    Prev
    Next
    INDEX
    Explanations

    institutions and organizations of various types

    oai_token-act-pair · gemini-2.0-flash

    Institution names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Portale
    -0.70
    LookAnd
    -0.66
    ----</
    -0.63
    LayoutConstraint
    -0.61
     ModelExpression
    -0.61
    Демографія
    -0.61
     direct
    -0.60
     AssemblyTitle
    -0.59
     Krim
    -0.58
    kedés
    -0.57
    POSITIVE LOGITS
    extAlignment
    0.63
     tillbaka
    0.57
    Aiheesta
    0.56
     igång
    0.55
     hjälper
    0.53
     stöd
    0.53
     sendiri
    0.52
     länge
    0.51
     demais
    0.50
     spalle
    0.50
    Activations Density 2.299%

    No Known Activations