© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9007
    Prev
    Next
    INDEX
    Explanations

    passages discussing the health and well-being of populations, especially in terms of nutrition, disease, and access to services.

    oai_token-act-pair · gemini-2.0-flash

    terms related to community and conflict

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

    micronutrient deficiencies and aid

    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
    beforeAll
    -0.48
     cancelación
    -0.46
    icose
    -0.45
    RectangleBorder
    -0.45
     BoxDecoration
    -0.44
     razas
    -0.44
    IBar
    -0.44
    jface
    -0.44
    racial
    -0.43
     pstmt
    -0.43
    POSITIVE LOGITS
    EndInit
    0.73
     village
    0.61
     rebel
    0.61
     donor
    0.60
    BeginContext
    0.60
    клопе
    0.58
     villagers
    0.58
    منابع
    0.58
     armed
    0.57
     villages
    0.56
    Activations Density 4.463%

    No Known Activations