© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10822
    Prev
    Next
    INDEX
    Explanations

    phone numbers, locations, and brands

    oai_token-act-pair · gemini-2.0-flash

    Locations, time, and money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ENOMEM
    -0.48
    springframework
    -0.46
    <eos>
    -0.45
     bar
    -0.44
     kelapa
    -0.41
     Bar
    -0.40
     H
    -0.40
    FATAL
    -0.40
     G
    -0.38
    }.
    -0.38
    POSITIVE LOGITS
     صوتيه
    0.90
     kasarigan
    0.85
     препратки
    0.81
     незавершена
    0.79
    Datuak
    0.78
    NameInMap
    0.77
    enumii
    0.76
    Personensuche
    0.76
     мәкал
    0.76
    setVerticalGroup
    0.76
    Activations Density 7.067%

    No Known Activations