© 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. 8012
    Prev
    Next
    INDEX
    Explanations

    JavaScript and related code syntax

    oai_token-act-pair · gemini-2.0-flash

    programming terms or functions

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

    Code/programming

    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
     رسد
    -0.43
    addContainerGap
    -0.43
    diyesi
    -0.43
     Oggi
    -0.42
    ofre
    -0.42
     rozho
    -0.41
    U
    -0.39
    ="@+
    -0.39
     farine
    -0.39
     droog
    -0.39
    POSITIVE LOGITS
    tvguidetime
    0.89
     disambiguazione
    0.87
    rungsseite
    0.79
     getSystem
    0.76
    RegressionTest
    0.75
     AppCompatTheme
    0.74
    MemoryWarning
    0.73
     Audiodateien
    0.72
    verwijspagina
    0.69
    AutoScaleMode
    0.69
    Activations Density 0.826%

    No Known Activations