© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13569
    Prev
    Next
    INDEX
    Explanations

    words related to directions and paths but not North/South/East/West.

    oai_token-act-pair · gemini-2.0-flash

    TOP_ACTIVATING_TEXTS seems to be related to trails or paths, and the max activating tokens often appear in the context of directions or descriptions of paths. Trails and paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    المناصب
    -0.83
    tagHelperRunner
    -0.78
     <>",
    -0.74
    RectangleBorder
    -0.66
     مشين
    -0.63
    IntoConstraints
    -0.63
    NOPQRST
    -0.61
    EDEFAULT
    -0.60
     referenties
    -0.59
     Мексичка
    -0.59
    POSITIVE LOGITS
     Dot
    0.48
     Bet
    0.48
     bet
    0.47
     dotted
    0.46
     amore
    0.46
    Dot
    0.45
    ToolStrip
    0.44
    al
    0.44
    dot
    0.43
    vägen
    0.43
    Activations Density 2.713%

    No Known Activations