© 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. 8696
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers, parentheses, and the words "and", "random", "nextInt", "float", "for", and "Instance"

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    клопе
    -0.74
    Personendaten
    -0.69
    complexContent
    -0.59
    :✨
    -0.54
     AssemblyTitle
    -0.53
     poffible
    -0.53
     pageContext
    -0.52
     <=",
    -0.51
     verstär
    -0.49
     caprice
    -0.49
    POSITIVE LOGITS
    mtrl
    0.56
    djangoproject
    0.55
    ichier
    0.54
    httphttps
    0.54
     NotImplemented
    0.53
    Reb
    0.50
    outons
    0.49
    BeginContext
    0.48
     فريبيس
    0.47
    perger
    0.46
    Activations Density 1.748%

    No Known Activations