© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11573
    Prev
    Next
    INDEX
    Explanations

    code for plotting scatter plots using numpy and matplotlib

    oai_token-act-pair · gemini-2.0-flash

    np

    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
    ënt
    -0.44
     Dhabi
    -0.42
     most
    -0.42
     kriti
    -0.42
     sor
    -0.41
    ⚕
    -0.41
    flashdata
    -0.41
     gra
    -0.41
    PageContext
    -0.40
     Most
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.82
     myſelf
    0.73
     becauſe
    0.72
     ſhe
    0.72
    DockStyle
    0.71
     obſ
    0.69
    ReusableCell
    0.69
    (!__
    0.68
    KommentareTeilen
    0.67
     reaſon
    0.67
    Activations Density 1.615%

    No Known Activations