© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    blocks of C code, especially conditionals and assignments

    oai_token-act-pair · gemini-2.0-flash

    code control structures

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

    if

    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
     виправивши
    -0.91
     beginnetje
    -0.89
    TestingModule
    -0.88
    thâu
    -0.77
     مشين
    -0.76
    AndEndTag
    -0.72
    DoubleQuotes
    -0.71
     Chriftian
    -0.70
     kaarangay
    -0.69
    hyrchwyd
    -0.68
    POSITIVE LOGITS
    missie
    0.48
    ecznie
    0.46
    enumi
    0.46
     tartalmaz
    0.43
     tovább
    0.42
     Ta
    0.41
     It
    0.41
    idase
    0.40
     hjem
    0.40
     contrats
    0.40
    Activations Density 1.009%

    No Known Activations