© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    words related to the function and performance of vehicle engines

    oai_token-act-pair · gemini-2.0-flash

    terms related to fuel consumption

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

    fuel or gas

    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
    DockStyle
    -0.77
    httphttps
    -0.67
    writeFieldEnd
    -0.65
    kmäler
    -0.61
    bootstrapcdn
    -0.61
    +:+
    -0.57
     Normdatei
    -0.57
     Turquie
    -0.56
     BnF
    -0.54
     Fiorentina
    -0.54
    POSITIVE LOGITS
     fuel
    1.78
     Fuel
    1.58
    Fuel
    1.48
     FUEL
    1.47
    fuel
    1.47
     gas
    1.27
    FUEL
    1.25
     gasoline
    1.17
     petrol
    1.14
     Gas
    1.11
    Activations Density 1.803%

    No Known Activations