© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6368
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to formal applications and associated documentation

    oai_token-act-pair · gemini-2.0-flash

    forms and letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ſche
    -0.74
    ientôt
    -0.73
     MainAxisSize
    -0.68
    VIAF
    -0.66
    ouvrage
    -0.65
     iſt
    -0.65
    omatic
    -0.64
     Monfieur
    -0.64
    Эзо
    -0.64
    DoubleQuotes
    -0.63
    POSITIVE LOGITS
     مشارکت‌کنندگان
    0.50
    sizeCache
    0.44
    তথ্যসূত্র
    0.43
     Administrativna
    0.42
    lag
    0.42
     figure
    0.41
    әрмәләр
    0.38
     org
    0.38
     SA
    0.38
    XtraEditors
    0.37
    Activations Density 3.118%

    No Known Activations