© 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. 10094
    Prev
    Next
    INDEX
    Explanations

    technical specifications and advantages of electrical devices

    oai_token-act-pair · gemini-2.0-flash

    terms related to technical specifications or features

    np_token-act-pair-logits · gpt-4o-mini
    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
    setFocusable
    -0.52
     nudo
    -0.48
    новништво
    -0.46
     createContext
    -0.46
    PRNewswire
    -0.46
    colata
    -0.46
    ENCES
    -0.45
    defn
    -0.45
    stateProvider
    -0.45
    kel
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.94
     برانيه
    0.78
     فريبيس
    0.75
    tagHelperRunner
    0.75
     صوتيه
    0.71
     numberWith
    0.67
    WithMany
    0.66
    iastes
    0.64
    ########.
    0.60
     تضيفلها
    0.60
    Activations Density 1.215%

    No Known Activations