© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8232
    Prev
    Next
    INDEX
    Explanations

    places and times that criminal acts occur

    oai_token-act-pair · gemini-2.0-flash

    say "night"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     féd
    -0.61
    perity
    -0.54
    bootstrapcdn
    -0.51
    BagLayout
    -0.50
    spesies
    -0.50
     }}"></
    -0.49
     Económica
    -0.47
    EndProject
    -0.47
     onData
    -0.46
    kaa
    -0.46
    POSITIVE LOGITS
     night
    2.11
     nights
    1.80
    night
    1.80
     Night
    1.73
    Night
    1.70
     NIGHT
    1.63
     nighttime
    1.52
     evening
    1.51
    nights
    1.49
     Nights
    1.47
    Activations Density 0.573%

    No Known Activations