© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10639
    Prev
    Next
    INDEX
    Explanations

    numbers between 1 and 4

    oai_token-act-pair · gemini-2.0-flash

    Numbers and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    eadilan
    -0.45
     duro
    -0.45
    dflare
    -0.43
     poh
    -0.40
    prozess
    -0.40
     rowspan
    -0.38
     vagues
    -0.38
    bloomberg
    -0.38
     Gough
    -0.37
     generali
    -0.37
    POSITIVE LOGITS
    QMetaType
    0.79
     للمعارف
    0.76
    featureID
    0.71
    principalColumn
    0.71
     pulumi
    0.64
    PreferredItem
    0.63
    NameInMap
    0.63
     <=",
    0.62
    RegistryLite
    0.62
    өз
    0.61
    Activations Density 3.776%

    No Known Activations