© 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. 12255
    Prev
    Next
    INDEX
    Explanations

    the word "fact"

    oai_token-act-pair · gemini-2.0-flash

    fact

    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
     يتيمه
    -0.85
     CreateTagHelper
    -0.81
     houſe
    -0.75
     pleaſure
    -0.72
     ―――――
    -0.70
     itſelf
    -0.69
    ----</
    -0.69
     Theſe
    -0.68
     Jefus
    -0.67
     ſtate
    -0.67
    POSITIVE LOGITS
    aculture
    0.52
    情
    0.51
     imageNamed
    0.50
     feit
    0.49
     việc
    0.48
    旦
    0.48
    fmt
    0.46
     оригіналу
    0.45
     Hurt
    0.45
     hecho
    0.44
    Activations Density 0.476%

    No Known Activations