© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13207
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to directing or manipulating events or objects, sometimes in a technical or conspiratorial context.

    oai_token-act-pair · gemini-2.0-flash

    control

    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
     control
    -1.34
     Control
    -1.27
    Control
    -1.26
    control
    -1.23
     controls
    -1.22
     CONTROL
    -1.19
     controlling
    -1.18
    CONTROL
    -1.10
     controlled
    -1.09
     Controlling
    -1.09
    POSITIVE LOGITS
     متعلقه
    0.75
     betweenstory
    0.69
    AndroidJUnit
    0.67
     ExecuteAsync
    0.67
    findpost
    0.67
    Референце
    0.66
    ThroughAttribute
    0.66
    sidemargin
    0.62
    Réalisation
    0.62
    లాలు
    0.62
    Activations Density 16.941%

    No Known Activations