© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "has" or "is"

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating status or condition

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

    has/have

    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
     is
    -0.62
     pinulongan
    -0.59
    matchCondition
    -0.54
    awtextra
    -0.54
    Rptr
    -0.54
     
    -0.52
    addPreferredGap
    -0.51
    reactstrap
    -0.50
    +#+#
    -0.50
    setupUi
    -0.47
    POSITIVE LOGITS
     become
    0.63
     ModelExpression
    0.61
     not
    0.54
     its
    0.54
     remain
    0.54
    PMailer
    0.53
     becoming
    0.52
     remained
    0.52
     prove
    0.50
    CodedInputStream
    0.50
    Activations Density 1.767%

    No Known Activations