© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    the word "the" and words that often follow it such as country, city, upcoming, and open

    oai_token-act-pair · gemini-2.0-flash

    country context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     vermelhas
    -0.71
    ']")
    -0.67
    Diweddarwch
    -0.67
     engraçadas
    -0.66
    Màu
    -0.64
    =$?
    -0.64
     getIs
    -0.61
     producteurs
    -0.60
     prêts
    -0.60
     colère
    -0.59
    POSITIVE LOGITS
    .
    0.44
    Extinguishing
    0.43
    BOD
    0.43
    stylesheet
    0.42
     value
    0.41
     Diretto
    0.40
     intptr
    0.40
     Croix
    0.40
     gom
    0.40
     flask
    0.39
    Activations Density 1.450%

    No Known Activations