© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5531
    Prev
    Next
    INDEX
    Explanations

    technical writing about power systems

    oai_token-act-pair · gemini-2.0-flash

    words related to power and operation

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

    Electricity and power

    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
    หวัด
    -0.47
    团
    -0.43
    cco
    -0.43
    nost
    -0.41
    mrt
    -0.40
    form
    -0.40
    ITRE
    -0.39
    orno
    -0.39
    orm
    -0.39
    ubre
    -0.39
    POSITIVE LOGITS
     run
    1.09
     powered
    1.02
     powering
    1.02
     operated
    1.00
     operate
    0.96
     powers
    0.94
     nahilalakip
    0.94
     Run
    0.94
     Operated
    0.93
    run
    0.93
    Activations Density 3.077%

    No Known Activations