© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    the keyword "if"

    oai_token-act-pair · gemini-2.0-flash

    if

    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
    <bos>
    -0.68
     gustan
    -0.42
     jeżeli
    -0.41
    coledì
    -0.40
    oraf
    -0.38
    jski
    -0.38
    ыре
    -0.37
    Distribuzione
    -0.36
     permesso
    -0.36
    żeli
    -0.36
    POSITIVE LOGITS
     виправивши
    0.90
    arrings
    0.80
     चीज़ों
    0.72
    upassen
    0.72
    MIDDLEWARE
    0.71
    MemoryWarning
    0.68
     jLabel
    0.68
     resourceCulture
    0.67
    ]")]
    0.67
    Tembelea
    0.65
    Activations Density 1.201%

    No Known Activations