© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10231
    Prev
    Next
    INDEX
    Explanations

    words related to research, law, medicine, and general importance.

    oai_token-act-pair · gemini-2.0-flash

    calls, demands

    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
     autorytatywna
    -0.65
     propOrder
    -0.62
    UnitTesting
    -0.61
    Personendaten
    -0.60
    ksikon
    -0.60
    annas
    -0.60
     ExecuteAsync
    -0.59
     Fenne
    -0.57
     Efq
    -0.57
     setInterval
    -0.57
    POSITIVE LOGITS
     calls
    1.21
     demands
    1.17
     call
    1.04
     Calls
    1.02
     demand
    1.02
     Demands
    1.01
     calling
    1.01
     demanding
    0.98
    demand
    0.96
     demanded
    0.94
    Activations Density 4.568%

    No Known Activations