© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1750
    Prev
    Next
    INDEX
    Explanations

    words that end with "ies", "es", "ed", "s" and a few keywords "include", "of" and some words starting with the letter "a"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     />;
    -0.54
    Finalmente
    -0.54
    ceptar
    -0.52
     }],
    -0.50
    Географија
    -0.49
    ifte
    -0.49
    acia
    -0.48
     VizieR
    -0.47
     Finalmente
    -0.47
    zä
    -0.46
    POSITIVE LOGITS
    RectangleBorder
    0.71
     صوتيه
    0.68
     @"/
    0.66
    webElementXpaths
    0.64
    expandindo
    0.64
     الحره
    0.61
    setVerticalGroup
    0.61
    хьтан
    0.59
    tonsoft
    0.57
     disambiguazione
    0.56
    Activations Density 0.540%

    No Known Activations