© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12189
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to databases, code, and structured data

    oai_token-act-pair · gemini-2.0-flash

    database code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    الحياه
    -0.63
     morire
    -0.60
     StringTokenizer
    -0.57
    Архівовано
    -0.57
    DockStyle
    -0.56
    LookAnd
    -0.55
    fortawesome
    -0.55
     Walkover
    -0.54
     CreateTagHelper
    -0.54
    BeginInit
    -0.52
    POSITIVE LOGITS
    ThemeOverlay
    0.54
    CPtr
    0.54
    HtmlAttribute
    0.51
    trine
    0.48
    gares
    0.47
    бли
    0.46
    Bronnen
    0.46
    prom
    0.45
    σου
    0.45
    xodo
    0.44
    Activations Density 2.123%

    No Known Activations