© 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. 10592
    Prev
    Next
    INDEX
    Explanations

    words related to computer networking, but also activates in other cases, such as discussion of legal interactions.

    oai_token-act-pair · gemini-2.0-flash

    communication and coordination

    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
    ParallelGroup
    -0.91
     للمعارف
    -0.79
     utafitiHapana
    -0.79
     Normdatei
    -0.70
    TagMode
    -0.69
    FontOfSize
    -0.67
    ształ
    -0.65
    ագրություններ
    -0.65
     AssemblyProduct
    -0.63
    ageo
    -0.63
    POSITIVE LOGITS
    internalType
    0.44
    ั้น
    0.43
    彼此
    0.43
     Internal
    0.42
    yles
    0.42
     inter
    0.42
    unt
    0.41
    EndInit
    0.41
     生命周期
    0.41
    edith
    0.41
    Activations Density 1.864%

    No Known Activations