© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6374
    Prev
    Next
    INDEX
    Explanations

    marketing requests asking for people to follow, like, or visit

    oai_token-act-pair · gemini-2.0-flash

    like

    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
    BufferException
    -0.73
     Савезне
    -0.69
    AndEndTag
    -0.68
    InitVars
    -0.64
    تفصیلات
    -0.63
     AssemblyCulture
    -0.62
    setVerticalGroup
    -0.62
    HtmlAttribute
    -0.61
     oprot
    -0.61
    TagMode
    -0.60
    POSITIVE LOGITS
     like
    3.06
     Like
    2.61
    Like
    2.59
    like
    2.47
     LIKE
    2.36
    LIKE
    2.08
     likes
    1.68
     seperti
    1.54
     Seperti
    1.40
     liked
    1.34
    Activations Density 3.750%

    No Known Activations