© 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. 4217
    Prev
    Next
    INDEX
    Explanations

    technical and mechanical concepts like switches, device functions, electricity, and water levels

    oai_token-act-pair · gemini-2.0-flash

    concepts related to power and electricity

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

    power and lights

    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
     Waray
    -0.58
     surla
    -0.56
    Autoritní
    -0.52
     lenker
    -0.52
     rhestr
    -0.48
     bağlantılar
    -0.47
     Band
    -0.46
    Teb
    -0.46
    Predecesor
    -0.44
    ISupport
    -0.44
    POSITIVE LOGITS
     power
    0.84
    power
    0.77
    Power
    0.61
     lights
    0.59
     powers
    0.58
     LIGHTS
    0.58
     electricity
    0.58
     Power
    0.58
    lights
    0.57
     POWER
    0.57
    Activations Density 2.707%

    No Known Activations