© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11781
    Prev
    Next
    INDEX
    Explanations

    the chemical elements hydrogen, oxygen, helium, and nitrogen, especially in the context of liquids and gasses

    oai_token-act-pair · gemini-2.0-flash

    Hydrogen and chemistry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    HomeAsUpEnabled
    -0.60
    HasForeignKey
    -0.57
    IntoConstraints
    -0.57
    RegistryLite
    -0.57
    addGap
    -0.57
    PreferredItem
    -0.56
     AttributeSet
    -0.55
    COUVER
    -0.54
    WaitGroup
    -0.51
     cherchés
    -0.50
    POSITIVE LOGITS
    alta
    0.52
     Eder
    0.51
    laze
    0.48
     inqu
    0.47
    pit
    0.46
    etch
    0.45
    ueba
    0.45
    lani
    0.44
     emits
    0.43
     ModelExpression
    0.43
    Activations Density 0.841%

    No Known Activations