© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5358
    Prev
    Next
    INDEX
    Explanations

    code that imports from the react-native library

    oai_token-act-pair · gemini-2.0-flash

    react

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    vartis
    -0.53
     manslaughter
    -0.52
    setTitle
    -0.51
    Enumerator
    -0.50
     sclerosis
    -0.50
    zema
    -0.49
    api
    -0.48
    off
    -0.47
     potuto
    -0.47
    webElementGuid
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.65
    NameInMap
    0.62
     transférez
    0.58
    MigrationBuilder
    0.58
    Referencies
    0.57
     transfieras
    0.57
    Nuorodos
    0.56
     ISNI
    0.54
     continúas
    0.54
     Roskov
    0.54
    Activations Density 0.153%

    No Known Activations