© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9402
    Prev
    Next
    INDEX
    Explanations

    mentions of abstract ideas or concepts and words related to decisions

    oai_token-act-pair · gemini-2.0-flash

    Realization or epiphany

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     we
    -2.34
     We
    -1.97
    We
    -1.91
    we
    -1.70
     мы
    -1.67
    Мы
    -1.34
     WE
    -1.34
     Мы
    -1.30
    我們
    -1.27
    我们
    -1.21
    POSITIVE LOGITS
    LikeLike
    0.53
    gación
    0.48
    ||}
    0.45
    })$}
    0.44
    ManyToOne
    0.44
     Unser
    0.44
    openConnection
    0.44
    HtmlAttribute
    0.43
    ouan
    0.43
    SpringRunner
    0.41
    Activations Density 15.993%

    No Known Activations