© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11335
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or requests for assistance

    oai_token-act-pair · gemini-2.0-flash

    variants of the word "appreciate"

    np_token-act-pair-logits · gpt-4o-mini

    appreciate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ujednoznacz
    -0.64
    DataAnnotations
    -0.58
     sumpay
    -0.57
    thâu
    -0.57
    VELOP
    -0.56
     GoogleFonts
    -0.53
     surla
    -0.52
     myſelf
    -0.52
     نسخ
    -0.49
     Paloma
    -0.49
    POSITIVE LOGITS
     appreciate
    2.20
     appreciated
    2.13
     appreciates
    1.91
     Appreciate
    1.81
     appreciation
    1.80
     appreciating
    1.71
    Appreciate
    1.66
    appreciated
    1.59
     Appreciation
    1.57
     appreci
    1.54
    Activations Density 3.589%

    No Known Activations