© 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. 10543
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are generally positive and descriptive

    oai_token-act-pair · gemini-2.0-flash

    Text excerpts

    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
    Tembelea
    -0.96
     AssemblyProduct
    -0.92
    Portale
    -0.84
     estekak
    -0.83
     anún
    -0.80
     enfans
    -0.79
     judiciales
    -0.75
    脚注の使い方
    -0.75
     kasarigan
    -0.73
    تقاوى
    -0.72
    POSITIVE LOGITS
     problem
    0.58
     sub
    0.57
     work
    0.57
    addGap
    0.56
    bootstrapcdn
    0.56
     or
    0.56
     care
    0.56
    issez
    0.55
     high
    0.55
     and
    0.55
    Activations Density 1.379%

    No Known Activations