© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13603
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are important facts, conclusions, or arguments, especially in an article

    oai_token-act-pair · gemini-2.0-flash

    adverbs of frequency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MigrationBuilder
    -0.72
    IUrlHelper
    -0.68
    ValueStyle
    -0.63
    PullParser
    -0.62
    PreferredItem
    -0.60
     consultato
    -0.60
    queryInterface
    -0.60
    +:+
    -0.59
    XMLSchema
    -0.58
     <>",
    -0.58
    POSITIVE LOGITS
     still
    1.79
     always
    1.76
    still
    1.56
    always
    1.48
     already
    1.42
     often
    1.41
     actually
    1.38
     usually
    1.35
     also
    1.32
    already
    1.27
    Activations Density 7.805%

    No Known Activations