© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3792
    Prev
    Next
    INDEX
    Explanations

    words related to inspiring actions or ideas.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     inspiration
    -2.64
     inspired
    -2.47
     Inspiration
    -2.30
    inspiration
    -2.27
    Inspiration
    -2.20
     Inspired
    -2.19
     inspire
    -2.16
     inspirations
    -2.16
     inspir
    -2.13
     inspira
    -2.13
    POSITIVE LOGITS
     الحره
    0.60
     nahilalakip
    0.60
     EconPapers
    0.54
     Meksiku
    0.53
    marle
    0.52
     ویکی‌پدیا
    0.51
    صه
    0.50
    Jeografia
    0.49
     Viana
    0.49
    ppins
    0.49
    Activations Density 2.870%

    No Known Activations