© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    chemical symbols, molecular formulas, and measurement units

    oai_token-act-pair · gemini-2.0-flash

    chemical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    庁
    -0.48
    <bos>
    -0.46
     estimés
    -0.46
    复制
    -0.46
    rungsseite
    -0.44
     tetrachloride
    -0.43
     all
    -0.43
    all
    -0.41
    PasswordField
    -0.41
     мото
    -0.40
    POSITIVE LOGITS
    ValueGeneration
    0.71
    etheless
    0.66
    ürlich
    0.65
    Diweddarwch
    0.64
    tingham
    0.62
    Espèce
    0.61
    ंदीखरीदारी
    0.61
    ChildScrollView
    0.61
     BoxDecoration
    0.59
    };*/
    0.59
    Activations Density 1.260%

    No Known Activations