© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6159
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and medical language

    oai_token-act-pair · gemini-2.0-flash

    Rationality and legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    pev
    -0.68
    ธ์
    -0.48
    WireFormat
    -0.47
    vice
    -0.46
    ಷ್
    -0.45
    ContextHolder
    -0.45
     perumahan
    -0.44
     όλα
    -0.44
     thảo
    -0.43
    ян
    -0.43
    POSITIVE LOGITS
     senses
    0.82
    __':
    0.73
    __":
    0.71
     Senses
    0.70
    ніципа
    0.66
     capacity
    0.65
    ⓧ
    0.65
    󠁣
    0.65
    الإنجليزية
    0.63
     rational
    0.62
    Activations Density 0.585%

    No Known Activations