© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6361
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific writing including formulas, numbers, units, and measurements

    oai_token-act-pair · gemini-2.0-flash

    research analysis

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — because most following tokens are space-prefixed

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     kasarigan
    -1.38
    RegressionTest
    -1.02
     pinulongan
    -1.01
    SequentialGroup
    -1.00
    featureID
    -0.98
    SharedCtor
    -0.90
    rungsseite
    -0.87
    IntoConstraints
    -0.87
     dAtA
    -0.85
    出版年
    -0.84
    POSITIVE LOGITS
    <bos>
    0.71
     NDEBUG
    0.59
     nephe
    0.56
     fluence
    0.56
     errno
    0.55
     carbonates
    0.55
    carboxylic
    0.55
     recrystal
    0.53
     gluon
    0.53
     desorption
    0.52
    Activations Density 9.989%

    No Known Activations