© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8161
    Prev
    Next
    INDEX
    Explanations

    the beginning syllables of the word "choose"

    oai_token-act-pair · gemini-2.0-flash

    cho

    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
    thâu
    -0.74
     الاطلاع
    -0.67
     Welle
    -0.61
     nephe
    -0.60
    astify
    -0.59
     isomer
    -0.59
    LEncoder
    -0.59
    getSeconds
    -0.57
    RegistryLite
    -0.56
    BagLayout
    -0.55
    POSITIVE LOGITS
    LookAnd
    0.60
    complexContent
    0.49
     Society
    0.49
    SuspendLayout
    0.47
    Tembelea
    0.46
    ->_
    0.46
    BeginInit
    0.46
    jspx
    0.46
     Freeze
    0.43
     onCreateView
    0.43
    Activations Density 0.281%

    No Known Activations