© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12969
    Prev
    Next
    INDEX
    Explanations

    positive, negative, and legal verbs and words.

    oai_token-act-pair · gemini-2.0-flash

    gone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     gone
    -1.80
     went
    -1.65
     goes
    -1.45
    went
    -1.41
     Gone
    -1.34
    gone
    -1.28
    Went
    -1.27
    goes
    -1.21
     Went
    -1.21
     going
    -1.20
    POSITIVE LOGITS
    出版年
    0.80
    richTextPanel
    0.79
    contentLoaded
    0.78
    QMetaType
    0.73
    
    0.73
     MonoBehaviour
    0.72
     dAtA
    0.72
     ExecuteAsync
    0.71
     disambiguazione
    0.70
    JspWriter
    0.70
    Activations Density 9.654%

    No Known Activations