© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    section numbers and references, especially in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    technical terms or structured data identifiers

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

    period

    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
    ٫
    -0.55
     nervios
    -0.44
    ½
    -0.43
     Schedule
    -0.43
    %@",
    -0.41
    DoubleQuotes
    -0.41
    ¼
    -0.40
    checkNotNull
    -0.40
     scoreless
    -0.39
     ½
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.90
    writeFieldEnd
    0.84
    numerusform
    0.82
    dafx
    0.82
    verwijspagina
    0.71
    VIAF
    0.71
    titleMargin
    0.71
     Chwiliwch
    0.70
    GEBURTSDATUM
    0.69
    bollah
    0.68
    Activations Density 3.939%

    No Known Activations