© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14732
    Prev
    Next
    INDEX
    Explanations

    C code bitwise operators and hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    MLLoader
    -0.78
    ItemBackground
    -0.77
    ImageContext
    -0.72
    AndEndTag
    -0.64
     Wherefore
    -0.63
    ificantly
    -0.61
     Himo
    -0.60
     Ahead
    -0.60
     albedo
    -0.60
     ahead
    -0.59
    POSITIVE LOGITS
     pé
    0.50
    nsw
    0.49
     multi
    0.49
     množ
    0.48
     Nueva
    0.48
     Abgerufen
    0.47
    Multi
    0.47
    TELL
    0.46
    原始内容存档于
    0.46
     oprot
    0.45
    Activations Density 3.879%

    No Known Activations