© 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. 11915
    Prev
    Next
    INDEX
    Explanations

    words relating to remote work, distance, and virtual communications.

    oai_token-act-pair · gemini-2.0-flash

    remote communication

    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
     Remote
    -1.10
     remote
    -1.09
    remote
    -1.02
    Remote
    -1.02
     REMOTE
    -0.90
     remotely
    -0.85
     virtual
    -0.81
     Virtual
    -0.77
    virtual
    -0.75
     remoto
    -0.74
    POSITIVE LOGITS
    InitVars
    0.74
     <<<<<<<<<<<<<<
    0.70
    AddTagHelper
    0.68
    MessageTagHelper
    0.67
     Arad
    0.65
    TemporalType
    0.62
    webElementXpaths
    0.61
     كومونز
    0.59
     gynhyrchwyd
    0.57
     برانيه
    0.57
    Activations Density 13.366%

    No Known Activations