© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3460
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to diet, nutritional deficiencies, and specific age groups.

    oai_token-act-pair · gemini-2.0-flash

    terms related to health and nutrition

    np_token-act-pair-logits · gpt-4o-mini

    social issues and health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     wśród
    -0.77
    among
    -0.76
     among
    -0.72
     parmi
    -0.69
     Among
    -0.67
    Among
    -0.64
     AMONG
    -0.63
    Parmi
    -0.60
     amongst
    -0.57
     Parmi
    -0.56
    POSITIVE LOGITS
    Manbalar
    0.59
     متعلقه
    0.50
     estimés
    0.49
     صوتيه
    0.49
     interfering
    0.49
     interfered
    0.49
     ischemia
    0.48
     violating
    0.48
    Pró
    0.48
    InstrumentedTest
    0.48
    Activations Density 6.259%

    No Known Activations