© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3095
    Prev
    Next
    INDEX
    Explanations

    words related to medical or legal disclaimers.

    oai_token-act-pair · gemini-2.0-flash

    erectile dysfunction and nitric oxide

    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
     aveug
    -0.51
     auprès
    -0.43
     färg
    -0.41
     prestazioni
    -0.39
    yari
    -0.39
     Superhosts
    -0.39
     termica
    -0.39
    seamnă
    -0.38
    INCREF
    -0.38
     épu
    -0.38
    POSITIVE LOGITS
    ContentAsync
    1.09
    UnusedPrivate
    0.79
     ModelExpression
    0.77
    UrlResolution
    0.69
    MockMvc
    0.67
    MouseClicked
    0.66
     AssemblyTitle
    0.65
    はじめに
    0.64
     समीक्षक
    0.63
     OMITBAD
    0.63
    Activations Density 0.830%

    No Known Activations