© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to electricity and power systems

    oai_token-act-pair · gemini-2.0-flash

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IntoConstraints
    -0.79
     jspb
    -0.57
    InputBorder
    -0.54
    帖最后由
    -0.54
    SBATCH
    -0.52
    Personendaten
    -0.50
    Cia
    -0.50
    éez
    -0.49
    جغرافيا
    -0.49
    ivably
    -0.48
    POSITIVE LOGITS
     оригіналу
    0.54
    ISupport
    0.51
    hadores
    0.47
     समीक्षाएं
    0.47
     faisons
    0.47
    breviation
    0.46
    SequentialGroup
    0.46
    ровки
    0.46
    OfBirth
    0.45
    )}_
    0.45
    Activations Density 2.478%

    No Known Activations