© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    text in a South-East Asian language such as Kannada

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    เหร
    -0.90
     การ์ตูน
    -0.87
    เกง
    -0.82
    ์ตูน
    -0.75
    เค้า
    -0.73
     วาด
    -0.73
    แหล
    -0.69
    ตาย
    -0.68
    หน้านี้
    -0.67
    ของคุณ
    -0.66
    POSITIVE LOGITS
    TagMode
    0.90
    หวัด
    0.82
    wpi
    0.79
     élevées
    0.73
    ษ
    0.72
    RepeatedField
    0.71
     connues
    0.71
     roux
    0.70
     connus
    0.70
    ท
    0.69
    Activations Density 0.682%

    No Known Activations