© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to travel, especially cruises and Mediterranean destinations

    oai_token-act-pair · gemini-2.0-flash

    Cruises

    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
    enumi
    -0.56
    indale
    -0.47
     vol
    -0.46
    ulam
    -0.45
    llano
    -0.45
    Pranala
    -0.44
     brug
    -0.44
     sillä
    -0.43
    entries
    -0.42
    ̀nh
    -0.42
    POSITIVE LOGITS
    MIDDLEWARE
    0.75
    InjectAttribute
    0.74
    исленность
    0.73
    RectangleBorder
    0.71
    tagHelperRunner
    0.70
    хьтан
    0.68
    MigrationBuilder
    0.66
    InitVars
    0.64
    errHandler
    0.62
    StoryboardSegue
    0.60
    Activations Density 0.150%

    No Known Activations