© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5802
    Prev
    Next
    INDEX
    Explanations

    technical discussions related to computers and networking, especially concerning Ubuntu

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    solution

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     enfans
    -0.75
     fidé
    -0.74
     présidenti
    -0.74
     Monfieur
    -0.73
     étoit
    -0.69
     domestiques
    -0.69
     auroit
    -0.67
     chrétien
    -0.66
     étoient
    -0.65
     sanitaires
    -0.65
    POSITIVE LOGITS
     OFDb
    0.57
     preciso
    0.47
    Saxon
    0.45
     et
    0.43
    нциклопедия
    0.42
     okolí
    0.42
    fiscal
    0.41
    urtz
    0.41
     gebeurt
    0.40
     à
    0.40
    Activations Density 8.829%

    No Known Activations