© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the energy industry and government policy

    oai_token-act-pair · gemini-2.0-flash

    specialized terms related to energy policies

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

    Governmental/financial reports

    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
    enterOuterAlt
    -0.73
    SourceChecksum
    -0.69
    atigable
    -0.63
    AnchorStyles
    -0.60
    InjectAttribute
    -0.60
     girder
    -0.59
     arşivlendi
    -0.58
     Meksiku
    -0.56
    Revenir
    -0.56
    الحياه
    -0.56
    POSITIVE LOGITS
    adaptiveStyles
    0.60
    featureID
    0.57
    Spel
    0.50
     fallu
    0.46
     Exchequer
    0.44
    kund
    0.43
     proof
    0.43
     Quang
    0.43
    Angleterre
    0.42
    abbaye
    0.42
    Activations Density 1.249%

    No Known Activations