© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14706
    Prev
    Next
    INDEX
    Explanations

    what looks like poorly translated text, possibly from Chinese

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     EconPapers
    -0.59
    +#+#
    -0.56
    لينكات
    -0.54
     toepassing
    -0.52
    BufferException
    -0.51
    المكان
    -0.51
    __':
    -0.48
    QMetaType
    -0.48
     esetén
    -0.47
     الاطلاع
    -0.47
    POSITIVE LOGITS
    TagMode
    0.63
    TintMode
    0.59
    OrFail
    0.57
    ariConfig
    0.55
    Havolalar
    0.54
    ioutil
    0.50
     betweenstory
    0.50
    Kaynakça
    0.50
    PhysRevD
    0.50
    iveau
    0.50
    Activations Density 4.670%

    No Known Activations