© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14356
    Prev
    Next
    INDEX
    Explanations

    words dealing with emotional states and dialogue

    oai_token-act-pair · gemini-2.0-flash

    story snippets

    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
    出版年
    -0.77
    Ligações
    -0.69
     wireType
    -0.60
    sidemargin
    -0.57
    OrBuilder
    -0.57
    addCriterion
    -0.54
    complexContent
    -0.52
    getSupport
    -0.52
     JADX
    -0.51
    aspectj
    -0.51
    POSITIVE LOGITS
     "..\..\
    0.70
     ویکی‌پدیای
    0.59
    MessageOf
    0.56
    ContentAsync
    0.55
    ExecuteReader
    0.55
    oa̍t
    0.55
     AssemblyTitle
    0.54
     propOrder
    0.54
     rev
    0.53
     Escri
    0.51
    Activations Density 3.392%

    No Known Activations