© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7638
    Prev
    Next
    INDEX
    Explanations

    the city of St. Louis and words ending in "ture"

    oai_token-act-pair · gemini-2.0-flash

    Louis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Hal
    -1.67
     hal
    -1.61
    Hal
    -1.52
    hal
    -1.43
     HAL
    -1.08
    HAL
    -1.00
     Louis
    -0.93
     متعلقه
    -0.85
    Louis
    -0.82
     advocate
    -0.81
    POSITIVE LOGITS
     mukana
    0.49
     filmen
    0.47
    ohne
    0.47
     suivantes
    0.45
     jól
    0.45
     Helms
    0.44
     generazione
    0.44
     ModelExpression
    0.44
    他对
    0.43
    lhe
    0.43
    Activations Density 1.123%

    No Known Activations