© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3747
    Prev
    Next
    INDEX
    Explanations

    different forms of the word "stop" and subsequent prepositions

    oai_token-act-pair · gemini-2.0-flash

    actions involving stopping or halting

    np_token-act-pair-logits · gpt-4o-mini

    stop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     stop
    -1.30
     stops
    -1.18
     stopped
    -1.18
     Stop
    -1.12
     Stops
    -1.09
     stopping
    -1.07
    stop
    -1.06
     STOP
    -1.05
     stopp
    -1.03
    Stop
    -1.00
    POSITIVE LOGITS
     CreateTagHelper
    0.50
     Ride
    0.47
     дел
    0.46
     subscribing
    0.45
    being
    0.45
     Offisielt
    0.44
    Ride
    0.44
     Navig
    0.43
    !*\
    0.42
     Dijo
    0.42
    Activations Density 4.721%

    No Known Activations