© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    words related to the asking of questions or the expression of conditions or situations

    oai_token-act-pair · gemini-2.0-flash

    Do

    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
    jsonwebtoken
    -0.63
     محفوظة
    -0.62
     esboço
    -0.58
     Unlocked
    -0.57
    NameInMap
    -0.56
    Rela
    -0.54
     nghi
    -0.52
     ISTAT
    -0.52
    rungsseite
    -0.51
    Demografie
    -0.51
    POSITIVE LOGITS
    </thead>
    0.53
     WebDriverWait
    0.52
     good
    0.51
    StructEnd
    0.50
    ruzione
    0.49
    IgnoreCase
    0.46
    rupt
    0.46
     UIApplication
    0.45
    رف
    0.44
    ConverterFactory
    0.44
    Activations Density 0.302%

    No Known Activations