© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12431
    Prev
    Next
    INDEX
    Explanations

    what appears to be words in the Malaysian language

    oai_token-act-pair · gemini-2.0-flash

    Multilingual/technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    diers
    -0.42
    anine
    -0.42
    \}^{
    -0.42
     ding
    -0.41
    lujah
    -0.40
    chio
    -0.39
    تفصیلات
    -0.38
     rapt
    -0.38
    евский
    -0.38
    驼
    -0.37
    POSITIVE LOGITS
     NSCoder
    0.93
    kloped
    0.70
     Reverso
    0.69
    principalColumn
    0.64
    ########.
    0.64
    RequestParam
    0.63
     EconPapers
    0.61
    QMetaType
    0.61
    قایناق‌لار
    0.60
    ValueGeneration
    0.59
    Activations Density 0.857%

    No Known Activations