© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6338
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions, especially those involving numbers, multiplication, and sometimes algebraic terms or hexadecimal code.

    oai_token-act-pair · gemini-2.0-flash

    code snippets and calculations

    np_max-act-logits · gemini-2.0-flash

    digits

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     منهم
    -0.44
    MethodInfo
    -0.40
     cukru
    -0.40
    sive
    -0.39
     infusion
    -0.39
    Brought
    -0.38
    inf
    -0.38
     Escor
    -0.38
    GLOBALS
    -0.37
    ווא
    -0.37
    POSITIVE LOGITS
    Демографія
    0.91
    RenderAtEndOf
    0.86
    AddTagHelper
    0.85
    tagHelperRunner
    0.81
    fjspx
    0.79
     ویکی‌پدی
    0.79
    migrationBuilder
    0.78
    ValueStyle
    0.77
    évaluateur
    0.75
    Referències
    0.72
    Activations Density 21.771%

    No Known Activations