© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 107
    Prev
    Next
    INDEX
    Explanations

    references to a victim or potential victim of a crime.

    oai_token-act-pair · gemini-2.0-flash

    victim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.61
    хьтан
    -0.53
     chó
    -0.48
    canestro
    -0.47
    Diwedd
    -0.46
     udaler
    -0.46
     taban
    -0.46
    ophyllum
    -0.45
     Cage
    -0.44
    lat
    -0.44
    POSITIVE LOGITS
     myſelf
    0.79
     houſe
    0.77
     purpoſe
    0.77
     Majefty
    0.76
     ſtate
    0.72
     Monfieur
    0.72
     raiſ
    0.71
     greateſt
    0.71
     leaſt
    0.70
     Houſe
    0.70
    Activations Density 3.903%

    No Known Activations