© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5849
    Prev
    Next
    INDEX
    Explanations

    sequences of periods and dashes in a document

    oai_token-act-pair · gemini-2.0-flash

    Non-English opening words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     насељу
    -0.73
    httphttps
    -0.71
    脚注の使い方
    -0.67
    GOTREF
    -0.66
    BASELINE
    -0.61
     INTERESAR
    -0.60
    contentLoaded
    -0.60
    migrationBuilder
    -0.59
    COUVER
    -0.59
     Exacts
    -0.57
    POSITIVE LOGITS
    <bos>
    0.54
     esperienza
    0.51
     initComponents
    0.50
    mazione
    0.45
     پذ
    0.45
     venía
    0.45
     вывод
    0.44
    navigator
    0.44
     répondre
    0.44
    บบ
    0.43
    Activations Density 0.541%

    No Known Activations