© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6605
    Prev
    Next
    INDEX
    Explanations

    words related to scientific writing or patents

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming concepts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     you
    -0.53
    Has
    -0.51
    gade
    -0.50
     religieuses
    -0.47
     kanyang
    -0.47
    spaceBetween
    -0.47
    pv
    -0.46
    出版年
    -0.46
    えています
    -0.45
    asai
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.66
    ніципалі
    0.66
    AddHtmlAttribute
    0.60
    BufferException
    0.57
     SwitchCompat
    0.56
    verständlich
    0.56
    DIPSETTING
    0.54
    drawal
    0.54
    assumption
    0.53
    itinéraire
    0.52
    Activations Density 3.010%

    No Known Activations