© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11533
    Prev
    Next
    INDEX
    Explanations

    the word "across"

    oai_token-act-pair · gemini-2.0-flash

    across

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     across
    -1.21
    across
    -1.02
     Across
    -1.01
    Across
    -0.98
     Bob
    -0.86
     ACROSS
    -0.85
    ArgsConstructor
    -0.75
     throughout
    -0.72
    Bob
    -0.71
     TestBed
    -0.70
    POSITIVE LOGITS
    ()]
    0.60
     entendido
    0.54
     Pró
    0.47
     ejus
    0.47
    DMETHOD
    0.46
     cương
    0.45
     ſhe
    0.45
    :')
    0.45
     căr
    0.44
     åt
    0.44
    Activations Density 0.295%

    No Known Activations