© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14249
    Prev
    Next
    INDEX
    Explanations

    terms related to environmentalism, health, sustainability, and related organizations

    oai_token-act-pair · gemini-2.0-flash

    sustainability 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.57
    原始内容存档于
    -0.54
    Tembelea
    -0.53
    impinan
    -0.50
    يميديا
    -0.48
     surla
    -0.48
     Prima
    -0.46
    Permalink
    -0.46
    Banned
    -0.46
    umi
    -0.46
    POSITIVE LOGITS
     typelib
    0.59
    ειτουργ
    0.59
    complexContent
    0.57
    FlatAppearance
    0.54
    nocache
    0.53
    ngOn
    0.52
    EDEFAULT
    0.51
    readystatechange
    0.50
     talent
    0.49
     متعلقه
    0.49
    Activations Density 6.019%

    No Known Activations