© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5955
    Prev
    Next
    INDEX
    Explanations

    "You" or "me" followed by words that could be interpreted as instructions or something being done or shown to someone.

    oai_token-act-pair · gemini-2.0-flash

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    djangoproject
    -0.81
     Meksiku
    -0.73
    хьтан
    -0.65
     disambiguazione
    -0.64
    bootstrapcdn
    -0.64
    CloseOperation
    -0.60
    parsedMessage
    -0.60
     Interceptor
    -0.60
     препратки
    -0.60
    Slf
    -0.60
    POSITIVE LOGITS
    styleUrls
    0.56
    HEAST
    0.52
    ítmény
    0.50
    usehen
    0.50
     could
    0.50
     investigators
    0.49
    findpost
    0.49
    oen
    0.48
     initComponents
    0.47
    셜
    0.47
    Activations Density 1.568%

    No Known Activations