© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2282
    Prev
    Next
    INDEX
    Explanations

    language related to teaching, education, and purpose

    oai_token-act-pair · gemini-2.0-flash

    teach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للمعارف
    -0.56
    luia
    -0.53
    adə
    -0.50
    onAttach
    -0.48
    inscription
    -0.47
    thâu
    -0.47
     stimulated
    -0.47
    __(/*!
    -0.46
    iações
    -0.45
    iação
    -0.45
    POSITIVE LOGITS
     صوتيه
    0.61
     spread
    0.57
     formales
    0.56
     formal
    0.56
    iffen
    0.55
    formal
    0.54
    principalTable
    0.54
    SuppressLint
    0.54
    MigrationBuilder
    0.54
    spread
    0.52
    Activations Density 5.073%

    No Known Activations