© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6592
    Prev
    Next
    INDEX
    Explanations

    conditional statements and related code elements in Java

    oai_token-act-pair · gemini-2.0-flash

    if/for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BeginContext
    -0.58
    RefNanny
    -0.57
    aarrggbb
    -0.57
    mergeFrom
    -0.54
    invokeLater
    -0.50
    Personendaten
    -0.49
    Спољашње
    -0.47
    onema
    -0.47
    #+#
    -0.47
    tionalität
    -0.47
    POSITIVE LOGITS
     ainfi
    0.66
     moschino
    0.66
     uintptr
    0.64
     Anſ
    0.63
     Bessel
    0.62
    bbene
    0.60
     PZ
    0.58
     pouvoit
    0.58
     NTB
    0.58
     Inscrivez
    0.57
    Activations Density 3.628%

    No Known Activations