© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration files that contain the string "ngx" and "X"

    oai_token-act-pair · gemini-2.0-flash

    X

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.68
     StringField
    -0.60
    VolleyError
    -0.60
    InputLabel
    -0.54
    tehen
    -0.54
     Connectez
    -0.53
    lld
    -0.52
    LEADING
    -0.52
    Slf
    -0.52
     '\\;'
    -0.51
    POSITIVE LOGITS
    ']->
    0.68
    ectoria
    0.65
    [])
    0.64
    tagHelperRunner
    0.64
    تقاوى
    0.63
    maxcdn
    0.63
     xăm
    0.62
     препратки
    0.61
    DebuggerNonUser
    0.59
     кӀ
    0.59
    Activations Density 6.147%

    No Known Activations