© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    the word "most"

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "most"

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

    most

    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
     resourceCulture
    -0.63
    fortawesome
    -0.48
    #
    -0.47
     Komis
    -0.43
     &___
    -0.43
     mantel
    -0.43
     EconPapers
    -0.41
     Diputados
    -0.41
     tartalomajánló
    -0.40
     Spal
    -0.40
    POSITIVE LOGITS
    </caption>
    0.66
    存于互联网档案馆
    0.62
    :✨
    0.57
    profen
    0.56
     Himo
    0.56
    SEGUIR
    0.55
    енча
    0.55
     MainAxisSize
    0.54
    NullCheck
    0.54
     Administrativna
    0.53
    Activations Density 0.211%

    No Known Activations