© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9484
    Prev
    Next
    INDEX
    Explanations

    mentions of nostalgic travel, particularly related to Howard Johnson's

    oai_token-act-pair · gemini-2.0-flash

    Travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    -0.55
    ObjectContext
    -0.49
    zahn
    -0.48
    opoly
    -0.46
    ochet
    -0.45
     okrąg
    -0.45
    tega
    -0.44
    ToListAsync
    -0.44
    ordon
    -0.43
    تقاوى
    -0.43
    POSITIVE LOGITS
     travelers
    0.75
    Traveling
    0.74
     referenties
    0.72
     Travel
    0.72
     travel
    0.70
     travellers
    0.69
     traveler
    0.66
     Travelling
    0.66
     traveling
    0.66
     noqa
    0.66
    Activations Density 0.897%

    No Known Activations