© 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. 14456
    Prev
    Next
    INDEX
    Explanations

    words related to medical, scientific, or pharmaceutical articles or journals

    oai_token-act-pair · gemini-2.0-flash

    the word 'both'

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

    "both"

    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
    tahui
    -0.65
     lizenzfreie
    -0.59
    SequentialGroup
    -0.57
     ویکی‌پدی
    -0.56
    guenos
    -0.55
    GIH
    -0.53
     surla
    -0.52
    المشاركات
    -0.52
     stránka
    -0.51
     câteva
    -0.50
    POSITIVE LOGITS
     both
    3.75
    both
    3.42
    Both
    3.22
     Both
    3.20
     BOTH
    2.72
    BOTH
    2.69
     entrambi
    2.34
    Ambos
    2.34
     Beide
    2.34
     ambos
    2.27
    Activations Density 4.100%

    No Known Activations