© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2314
    Prev
    Next
    INDEX
    Explanations

    lines of Java code

    oai_token-act-pair · gemini-2.0-flash

    Java/Android code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    NameInMap
    -0.69
     Eder
    -0.49
     Rollo
    -0.47
    code
    -0.47
    ajs
    -0.46
    jap
    -0.46
    jbl
    -0.45
    afficheront
    -0.44
    ansa
    -0.43
    anos
    -0.42
    POSITIVE LOGITS
    stateMutability
    0.75
    othelioma
    0.62
     كومونز
    0.62
    ituary
    0.61
    illaume
    0.60
    uyler
    0.59
     mergeFrom
    0.57
    Demografía
    0.57
    égorie
    0.56
    InvalidProtocol
    0.56
    Activations Density 0.378%

    No Known Activations