© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13780
    Prev
    Next
    INDEX
    Explanations

    specific chemical compound terms in chemistry and biology texts, often denoted by specific formatting such as brackets or capital letters.

    oai_token-act-pair · gemini-2.0-flash

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    radio
    -0.47
    ↵
    -0.42
    Radio
    -0.41
     radioactive
    -0.40
     radio
    -0.40
    Демографія
    -0.40
     Radio
    -0.39
    yntaxException
    -0.39
    }(),
    -0.39
     szcz
    -0.38
    POSITIVE LOGITS
    adaptiveStyles
    0.76
    berdayakan
    0.72
     pinulongan
    0.68
    ChildScrollView
    0.66
    TextWatcher
    0.66
    plevel
    0.65
     ſta
    0.65
     stiefel
    0.64
     Theſe
    0.64
    LayoutConstraint
    0.64
    Activations Density 47.793%

    No Known Activations