© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8941
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to current events, politics, and military actions

    oai_token-act-pair · gemini-2.0-flash

    the term "exercise"

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

    exercise

    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
    AndEndTag
    -0.66
    complexContent
    -0.57
    tagHelperRunner
    -0.55
    posedge
    -0.53
     Arp
    -0.49
    lapp
    -0.46
    textTheme
    -0.46
     beheaded
    -0.45
    __':
    -0.44
     koch
    -0.43
    POSITIVE LOGITS
     Exercise
    0.95
     exercise
    0.92
    Exercise
    0.88
     exercises
    0.84
    exercise
    0.80
    oa̍t
    0.80
     Exercises
    0.76
     EXERCISE
    0.75
     exercice
    0.74
     exercices
    0.71
    Activations Density 1.185%

    No Known Activations