© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    present simple tense verbs

    oai_token-act-pair · gemini-2.0-flash

    programming keywords

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

    Opinions, arguments

    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
    closedir
    -0.48
    ọc
    -0.46
    risse
    -0.45
    paque
    -0.44
    SCRIBE
    -0.43
     '\\;'
    -0.43
    oluble
    -0.42
    GetEnumerator
    -0.42
     Wikiquote
    -0.41
     jegy
    -0.41
    POSITIVE LOGITS
    addCriterion
    0.84
     for
    0.81
    AccessorTable
    0.79
     FOR
    0.75
     Pro
    0.73
    errHandler
    0.73
    for
    0.71
     For
    0.69
    ArrowToggle
    0.68
     pro
    0.68
    Activations Density 0.820%

    No Known Activations