© 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. 7896
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to replacing brake pads on a car

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

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

    Non-English words

    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
     Monfieur
    -0.77
     Houſe
    -0.72
     Efq
    -0.71
     Cæsar
    -0.67
     Jefus
    -0.65
     ſche
    -0.65
    AndEndTag
    -0.63
     houſe
    -0.63
    weeds
    -0.62
     Majefty
    -0.62
    POSITIVE LOGITS
    はじめに
    0.58
    KommentareTeilen
    0.54
    ReusableCell
    0.51
     diman
    0.48
    ಾಯ
    0.47
    routeProvider
    0.47
    нан
    0.45
    ken
    0.45
    Tembelea
    0.44
    MemoryWarning
    0.44
    Activations Density 1.202%

    No Known Activations