© 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. 10712
    Prev
    Next
    INDEX
    Explanations

    language used to dismiss an idea

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    ValueStyle
    -0.58
     Loy
    -0.45
     الحره
    -0.43
    indicate
    -0.42
    messageInfo
    -0.42
    classID
    -0.39
     ชั้น
    -0.39
     ungu
    -0.38
    ItemLayout
    -0.38
    jsonwebtoken
    -0.37
    POSITIVE LOGITS
     оригіналу
    0.63
     CreateTagHelper
    0.60
    gerton
    0.60
    RetentionPolicy
    0.59
     nakalista
    0.58
    MemoryWarning
    0.57
    SuspendLayout
    0.57
    kmäler
    0.56
    viewDidLoad
    0.55
     Eater
    0.55
    Activations Density 1.470%

    No Known Activations