© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to online accounts and payment options

    oai_token-act-pair · gemini-2.0-flash

    coded terminology or programming concepts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.65
    Controllo
    -0.54
    RTLR
    -0.52
     تكبرها
    -0.50
    رشف
    -0.49
    SourceChecksum
    -0.49
     Prise
    -0.49
    onViewCreated
    -0.49
     Overcome
    -0.48
     asma
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.93
    ък
    0.59
    IVEREF
    0.57
    addCriterion
    0.57
     Meksiku
    0.51
     cung
    0.51
     fills
    0.50
    PreAuthorize
    0.50
    nloa
    0.49
    WriteLiteral
    0.49
    Activations Density 1.742%

    No Known Activations