© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4239
    Prev
    Next
    INDEX
    Explanations

    text that appears to be fragments of math equations, code, or formal proofs.

    oai_token-act-pair · gemini-2.0-flash

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     المعيارى
    -1.00
    tvguidetime
    -0.91
    Autoritní
    -0.91
    ']))
    -0.86
    Šaltiniai
    -0.86
    rungsseite
    -0.85
    Personendaten
    -0.84
    évaluateur
    -0.81
     متعلقه
    -0.80
    ंदीखरीदारी
    -0.79
    POSITIVE LOGITS
    Red
    0.44
    red
    0.43
    НИК
    0.39
     iga
    0.39
    MathML
    0.38
    ism
    0.38
     autonomie
    0.37
    变形
    0.37
    pro
    0.36
     franco
    0.36
    Activations Density 11.771%

    No Known Activations