© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15244
    Prev
    Next
    INDEX
    Explanations

    words describing physical sensations and actions, especially those associated with violence, or submissiveness or deference

    oai_token-act-pair · gemini-2.0-flash

    injury/violence

    np_max-act-logits · 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
    parsedMessage
    -0.58
    ValueStyle
    -0.56
    mybatisplus
    -0.55
    réhen
    -0.52
    awtextra
    -0.52
    Viited
    -0.52
    elemField
    -0.52
    TimeUnit
    -0.52
     MenuView
    -0.51
    KURZBESCHREIBUNG
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.59
    tabular
    0.59
    ToListAsync
    0.54
    disposing
    0.52
    ernoo
    0.50
     فريبيس
    0.49
     MainAxisSize
    0.49
    portál
    0.49
     tartalomajánló
    0.48
     OMITBAD
    0.48
    Activations Density 5.807%

    No Known Activations