© 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. 14591
    Prev
    Next
    INDEX
    Explanations

    equations and math formulas.

    oai_token-act-pair · 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
     betweenstory
    -1.04
    SharedCtor
    -0.93
    ValueStyle
    -0.85
    PreferredItem
    -0.84
    setVerticalGroup
    -0.84
    сылкі
    -0.77
    ItemBackground
    -0.71
    +:+
    -0.71
    Personensuche
    -0.70
     linkovi
    -0.69
    POSITIVE LOGITS
     thác
    0.47
    NullCheck
    0.46
    ($__
    0.45
     quoi
    0.41
    ges
    0.40
    assertIs
    0.40
    asc
    0.39
    حاب
    0.39
    2
    0.38
     CURIAM
    0.38
    Activations Density 2.958%

    No Known Activations