© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13817
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be identifying sections of code, possibly related to API requests, string manipulation, or gulp tasks in JavaScript.

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    LookAnd
    -1.24
     فريبيس
    -1.20
     تضيفلها
    -1.17
    addCriterion
    -1.09
    MigrationBuilder
    -1.07
    tagHelperRunner
    -1.05
    principalTable
    -1.02
    AddTagHelper
    -1.01
     disambiguazione
    -0.99
     насељу
    -0.96
    POSITIVE LOGITS
     grecque
    0.31
    ↵↵
    0.31
     podido
    0.28
     epidem
    0.28
     kapas
    0.27
     africana
    0.27
     traitements
    0.27
    دار
    0.27
     coe
    0.27
     nedan
    0.26
    Activations Density 7.388%

    No Known Activations