© 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. 15083
    Prev
    Next
    INDEX
    Explanations

    uses of the word "on" or "the" specifically when preceded by particular other words

    oai_token-act-pair · gemini-2.0-flash

    say "board"

    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
     board
    -3.02
     Board
    -2.95
     boards
    -2.86
    Board
    -2.83
     Boards
    -2.77
    board
    -2.75
     BOARD
    -2.73
    BOARD
    -2.56
    boards
    -2.53
    Boards
    -2.48
    POSITIVE LOGITS
    jface
    0.46
    
    0.45
    ünsche
    0.44
    ceğim
    0.43
    Források
    0.43
    NameInMap
    0.42
     vriende
    0.42
    ovács
    0.41
    abstractmethod
    0.40
    россий
    0.40
    Activations Density 1.240%

    No Known Activations