© 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. 12622
    Prev
    Next
    INDEX
    Explanations

    the word "with" preceded or followed by words that describe an attitude or degree

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating significant tasks or actions

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

    with

    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
     AssemblyCulture
    -0.60
    ChildScrollView
    -0.60
     '\\;'
    -0.54
    Naissance
    -0.54
    ніципалі
    -0.53
     Decl
    -0.50
    \{\\
    -0.49
    urgo
    -0.49
    着
    -0.48
    mless
    -0.48
    POSITIVE LOGITS
     impunity
    0.55
     apl
    0.54
    DeleteBehavior
    0.53
    Sucesor
    0.53
     vigour
    0.53
     Biôgrafia
    0.53
    elemField
    0.52
     caution
    0.52
     ease
    0.51
     gusto
    0.51
    Activations Density 2.844%

    No Known Activations