© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    word fragments that end in "log", "rop", "ar", or otherwise contain the letters "o", "t", "s" and/or "c" together.

    oai_token-act-pair · gemini-2.0-flash

    categor

    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
     للاسماء
    -0.88
    Geografía
    -0.63
    chafter
    -0.60
    Посилання
    -0.60
     timedelta
    -0.59
    LayoutConstraint
    -0.58
    copa
    -0.58
    URIComponent
    -0.58
    timedelta
    -0.57
    enumi
    -0.57
    POSITIVE LOGITS
    SourceChecksum
    0.48
    UserScript
    0.46
    IsMutable
    0.43
     gawas
    0.41
     defaultstate
    0.40
    setOnItem
    0.39
     متعلقه
    0.39
    ();)
    0.38
    odyne
    0.37
    etna
    0.37
    Activations Density 2.255%

    No Known Activations