© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    words related to travel and tourism, especially hotels and accommodation

    oai_token-act-pair · gemini-2.0-flash

    place to stay

    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
    expandindo
    -0.59
     estekak
    -0.56
    MockBean
    -0.47
    Twice
    -0.47
     jalur
    -0.43
     congi
    -0.41
     zav
    -0.40
    twice
    -0.40
     الجد
    -0.40
    ORDS
    -0.40
    POSITIVE LOGITS
     surla
    0.81
    хьтан
    0.72
    dafx
    0.72
     Meksiku
    0.66
    httphttps
    0.63
    
    0.63
    apimachinery
    0.63
     CreateTagHelper
    0.60
     FetchType
    0.60
    reszcie
    0.59
    Activations Density 0.264%

    No Known Activations