© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12122
    Prev
    Next
    INDEX
    Explanations

    the letters 'Ch' at the beginning of words and numbers, presumably to flag Chinese-related content

    oai_token-act-pair · gemini-2.0-flash

    Starts with "Ch"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    談社
    -0.59
     ویکی‌پدیای
    -0.58
    хьтан
    -0.57
    webElement
    -0.54
    Legenda
    -0.54
     unknownFields
    -0.53
     utafitiHapana
    -0.52
     jLabel
    -0.52
    eait
    -0.51
    leftarrow
    -0.50
    POSITIVE LOGITS
     الرياضيه
    0.75
    is
    0.56
    ัติ
    0.55
    例文帳に追加
    0.54
    awtextra
    0.54
    <bos>
    0.52
    ính
    0.49
    GARET
    0.49
    PhysRev
    0.48
    alians
    0.48
    Activations Density 2.709%

    No Known Activations