© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14430
    Prev
    Next
    INDEX
    Explanations

    conditional keywords and symbols found in programming code

    oai_token-act-pair · gemini-2.0-flash

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    VOS
    -0.48
    ylla
    -0.48
    Aholisi
    -0.47
     anfangen
    -0.46
     localized
    -0.46
    ాని
    -0.45
     begren
    -0.45
    ┻
    -0.44
    valg
    -0.44
     féminine
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    ViewFeatures
    0.70
     onCreateView
    0.64
    ########.
    0.63
    RetentionPolicy
    0.62
    PerformLayout
    0.60
     متعلقه
    0.60
    MIDDLEWARE
    0.57
    RectangleBorder
    0.57
     سكانية
    0.56
    Activations Density 0.097%

    No Known Activations