© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14562
    Prev
    Next
    INDEX
    Explanations

    words related to the continuation, provision, or origin of something

    oai_token-act-pair · gemini-2.0-flash

    terms related to energy flow and supply

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

    flow/stream

    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
    ⓧ
    -0.75
    ineno
    -0.70
    UrlResolution
    -0.66
     nahilalakip
    -0.62
    enumi
    -0.61
    EndProject
    -0.58
    èdia
    -0.58
    setVerticalGroup
    -0.57
     <=",
    -0.57
    :+:
    -0.57
    POSITIVE LOGITS
     flow
    1.95
     stream
    1.88
    flow
    1.63
     Flow
    1.54
    Flow
    1.51
    stream
    1.46
     flows
    1.46
     Stream
    1.42
     flowing
    1.41
     streams
    1.39
    Activations Density 2.658%

    No Known Activations