© 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. 14787
    Prev
    Next
    INDEX
    Explanations

    code syntax characters and related words

    oai_token-act-pair · gemini-2.0-flash

    programming constructs or components

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

    code terms

    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
    Portail
    -0.56
     its
    -0.52
    خابات
    -0.50
     who
    -0.50
    ieb
    -0.48
     Ceux
    -0.47
    urm
    -0.47
     whatever
    -0.44
    stine
    -0.44
     anymore
    -0.43
    POSITIVE LOGITS
    ChildScrollView
    0.91
    
    0.87
     Normdatei
    0.85
     autorytatywna
    0.82
     GenerationType
    0.82
    RegressionTest
    0.81
     AssemblyCulture
    0.80
    enterOuterAlt
    0.79
    SequentialGroup
    0.77
    expandindo
    0.76
    Activations Density 12.465%

    No Known Activations