© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    the word "end" or "ends" followed by "up" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     End
    -0.62
    letzt
    -0.57
    roach
    -0.54
    止
    -0.53
    mouseleave
    -0.53
     кислота
    -0.49
     nuclé
    -0.49
    End
    -0.48
     end
    -0.48
     plomo
    -0.47
    POSITIVE LOGITS
     up
    0.79
     lenker
    0.73
     تضيفلها
    0.66
     down
    0.66
     hereto
    0.57
    VIAF
    0.57
    webElementXpaths
    0.56
     autorytatywna
    0.56
    ſelf
    0.54
     يتيمه
    0.54
    Activations Density 3.271%

    No Known Activations