© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2239
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to conditional statements and object properties.

    oai_token-act-pair · gemini-2.0-flash

    say "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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     if
    -2.70
     If
    -2.25
    If
    -1.95
     если
    -1.80
     jika
    -1.77
     dacă
    -1.77
     IF
    -1.67
    if
    -1.66
     nếu
    -1.63
     якщо
    -1.60
    POSITIVE LOGITS
    ंदीखरीदारी
    0.52
    neurial
    0.49
    haru
    0.48
     latter
    0.47
    parseDouble
    0.46
     $#
    0.46
     }^{
    0.46
    jari
    0.46
     '../../../
    0.45
    atol
    0.45
    Activations Density 2.307%

    No Known Activations