© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13095
    Prev
    Next
    INDEX
    Explanations

    code or code snippets in different programming languages like Javascript, German, and Portuguese

    oai_token-act-pair · gemini-2.0-flash

    "he" in other languages

    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
     propOrder
    -0.81
     they
    -0.76
     समीक्षाएं
    -0.70
     herself
    -0.60
     تضيفلها
    -0.59
     فريبيس
    -0.59
     CreateTagHelper
    -0.58
    qtype
    -0.58
     LoggerFactory
    -0.57
     विश्वसनीयता
    -0.57
    POSITIVE LOGITS
     he
    2.16
    He
    1.72
     He
    1.66
     он
    1.57
    他
    1.48
     him
    1.46
     그는
    1.38
    he
    1.36
     他
    1.34
    그는
    1.32
    Activations Density 0.826%

    No Known Activations