© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10823
    Prev
    Next
    INDEX
    Explanations

    numbers that include decimal points, as well as units of measure, percentages, and other notations

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    sidemargin
    -0.74
    RegressionTest
    -0.70
    Diwedd
    -0.64
    findpost
    -0.56
    setVerticalGroup
    -0.56
    DOCTYPE
    -0.55
     proprement
    -0.55
    BufferException
    -0.54
     beginnetje
    -0.54
     antaranya
    -0.53
    POSITIVE LOGITS
    InstanceState
    0.55
     насеље
    0.53
    +#+#
    0.49
    IsContent
    0.49
     dialed
    0.47
    MASK
    0.46
    mbic
    0.46
    MemoryWarning
    0.46
    ++
    0.45
    ContentAsync
    0.44
    Activations Density 1.556%

    No Known Activations