© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5367
    Prev
    Next
    INDEX
    Explanations

    the words "this", "that", "my", "the" and "a". It seems to be triggered by pronouns and articles

    oai_token-act-pair · gemini-2.0-flash

    references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     trends
    -0.90
     thoughts
    -0.88
     words
    -0.87
     observations
    -0.85
     symptoms
    -0.85
     secrets
    -0.84
     sentiments
    -0.84
     errors
    -0.83
     signs
    -0.83
     mistakes
    -0.83
    POSITIVE LOGITS
     navires
    0.50
     églises
    0.48
     consultato
    0.47
     vaisseaux
    0.46
     gouvernements
    0.46
    etano
    0.45
    ungsver
    0.42
    adaptiveStyles
    0.41
    TRIBUN
    0.40
    āda
    0.40
    Activations Density 3.779%

    No Known Activations