© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7704
    Prev
    Next
    INDEX
    Explanations

    mentions of hands or the floor, possibly a common phrase, or potentially small numbers or separators

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     فريبيس
    -0.58
    Personensuche
    -0.57
     hand
    -0.54
    '}),
    -0.52
     Amp
    -0.49
     Мексичка
    -0.48
     Sign
    -0.47
    \{\\
    -0.47
    MEN
    -0.46
     BrowserModule
    -0.46
    POSITIVE LOGITS
    SizeMode
    0.62
    WriteTagHelper
    0.56
    ForRow
    0.54
    HttpPut
    0.54
    MockBean
    0.51
     Jefus
    0.51
     Geol
    0.51
    BagConstraints
    0.50
    ContentAsync
    0.49
     wireType
    0.49
    Activations Density 3.071%

    No Known Activations