© 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
    2. Gemma-2-2B
    3. 18-GEMMASCOPE-TRANSCODER-16K
    4. 7667
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the process of learning and teaching.

    oai_token-act-pair · gemini-2.0-flash

    learning and resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    fjspx
    -0.74
    ⎯
    -0.71
    //
    -0.70
     ویکی‌پدی
    -0.70
    queryInterface
    -0.70
     ―――――
    -0.67
     décédé
    -0.66
     Plane
    -0.66
     plane
    -0.66
    gnition
    -0.65
    POSITIVE LOGITS
    resource
    0.43
     $
    0.43
    Cyfeiriadau
    0.43
    res
    0.42
     resource
    0.41
     recursos
    0.41
     Resource
    0.40
     to
    0.40
    new
    0.39
     odpor
    0.39
    Activations Density 3.405%

    No Known Activations