© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    text discussing AI or neural networks

    oai_token-act-pair · gemini-2.0-flash

    terms related to artificial intelligence

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

    AI

    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
    chowa
    -0.56
    zeptember
    -0.51
    +#+#
    -0.50
    órico
    -0.48
     poži
    -0.48
    AnimationsModule
    -0.48
     gönder
    -0.47
    sterdam
    -0.47
    zner
    -0.47
     déchir
    -0.47
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.61
     artificial
    0.59
     AI
    0.59
    etree
    0.58
     machine
    0.58
     '\\;'
    0.58
     mergeFrom
    0.57
    ANTLR
    0.57
     []:
    0.55
     Artificial
    0.54
    Activations Density 4.162%

    No Known Activations