© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    text related to power generation and thermodynamic cycles.

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms or proper nouns

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

    engines and power generation

    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
     fuel
    -1.18
     Fuel
    -1.06
    Fuel
    -1.00
     FUEL
    -0.96
    fuel
    -0.93
    FUEL
    -0.82
     fuels
    -0.77
     топлива
    -0.75
     gasoline
    -0.73
     petrol
    -0.72
    POSITIVE LOGITS
    FFIX
    0.50
    DockStyle
    0.47
     Turquie
    0.46
     Arp
    0.46
     vergeben
    0.46
     Levi
    0.46
    InputLabel
    0.46
     commandé
    0.46
    qrst
    0.45
     congé
    0.44
    Activations Density 0.785%

    No Known Activations