© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8957
    Prev
    Next
    INDEX
    Explanations

    special characters and measurements and related terms, often in scientific/technical contexts.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ابط
    -0.42
    /**
    -0.41
    InputBorder
    -0.41
     disambiguazione
    -0.40
    [][
    -0.38
     دریافت‌شده
    -0.38
    REQUEST
    -0.37
     Gattung
    -0.37
    +:+
    -0.36
    databind
    -0.35
    POSITIVE LOGITS
    DockStyle
    0.87
     Theſe
    0.79
     Савезне
    0.79
     ſeveral
    0.79
    ſelf
    0.79
     myſelf
    0.78
     Monfieur
    0.77
    ſelves
    0.75
     EconPapers
    0.75
     purpoſe
    0.75
    Activations Density 3.348%

    No Known Activations