© 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. 7699
    Prev
    Next
    INDEX
    Explanations

    tokens used to denote a figure, panel, display, equation, or other numbered item

    oai_token-act-pair · gemini-2.0-flash

    say "panel"

    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
     panel
    -2.80
     Panel
    -2.78
     panels
    -2.75
     Panels
    -2.66
    Panel
    -2.55
     PANEL
    -2.53
    panel
    -2.52
    PANEL
    -2.33
    Panels
    -2.31
    panels
    -2.28
    POSITIVE LOGITS
     فريبيس
    0.60
     يتيمه
    0.54
    Архівовано
    0.53
    protoimpl
    0.48
    Билгалдахарш
    0.48
    Ծանոթ
    0.46
    aglia
    0.45
    Kaynakça
    0.45
     actionTypes
    0.45
    inction
    0.44
    Activations Density 2.066%

    No Known Activations