© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5763
    Prev
    Next
    INDEX
    Explanations

    words related to search engines and bias in algorithms, and anything custom.

    oai_token-act-pair · gemini-2.0-flash

    engine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.63
    ↵
    -0.57
     and
    -0.52
    '
    -0.45
    -
    -0.45
    A
    -0.41
    1
    -0.40
    4
    -0.36
     
    -0.35
     T
    -0.35
    POSITIVE LOGITS
     Normdatei
    1.05
     propOrder
    0.96
     ExecuteAsync
    0.93
     CreateTagHelper
    0.86
    Билгалдахарш
    0.85
     صوتيه
    0.85
    IsMutable
    0.85
     تضيفلها
    0.85
    Tembelea
    0.83
     Chwiliwch
    0.82
    Activations Density 3.218%

    No Known Activations