© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    code snippets that refer to arrays, lists, elements, and data structures

    oai_token-act-pair · gemini-2.0-flash

    array

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Datuak
    -1.05
     виправивши
    -0.91
    OGND
    -0.89
     Efq
    -0.87
    تقاوى
    -0.85
     itſelf
    -0.84
    contentLoaded
    -0.83
    Personensuche
    -0.82
    ьаж
    -0.81
     متعلقه
    -0.81
    POSITIVE LOGITS
     of
    0.50
     form
    0.47
     –
    0.42
    athers
    0.39
     قالب
    0.39
    form
    0.36
    .
    0.35
    literal
    0.35
    通
    0.34
     mo
    0.34
    Activations Density 2.922%

    No Known Activations