© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14544
    Prev
    Next
    INDEX
    Explanations

    words generally related to travel and official procedures.

    oai_token-act-pair · gemini-2.0-flash

    trips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     trip
    -1.07
    trip
    -1.02
     tours
    -0.98
     tour
    -0.94
    Trip
    -0.94
     trips
    -0.91
     Trip
    -0.90
    tour
    -0.85
    trips
    -0.84
     Trips
    -0.82
    POSITIVE LOGITS
     Baillargeon
    0.52
    WarningLevel
    0.47
    merce
    0.44
    -"
    0.43
    Prerequisites
    0.42
    候
    0.41
     Schreib
    0.41
    seca
    0.40
    落下
    0.39
    —
    0.39
    Activations Density 35.770%

    No Known Activations