© 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. 9098
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially PHP code interacting with a database

    oai_token-act-pair · gemini-2.0-flash

    words related to database queries

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    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
    ContentAsync
    -0.76
    fjspx
    -0.59
    FieldBuilder
    -0.54
    awaiter
    -0.54
    __":
    -0.53
    AddTagHelper
    -0.52
    writeFieldEnd
    -0.50
    WriteTagHelper
    -0.50
    ậy
    -0.49
     affitto
    -0.49
    POSITIVE LOGITS
     Annu
    0.57
    urige
    0.55
     Winder
    0.54
    +#+#
    0.52
    culously
    0.52
    quins
    0.52
     diligen
    0.51
    byshev
    0.51
     offerings
    0.51
     للمعارف
    0.51
    Activations Density 0.220%

    No Known Activations