© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    words related to the Japanese language

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     oon
    -0.38
    EMBRE
    -0.33
     Gehen
    -0.33
    Г
    -0.33
    В
    -0.32
     Nowy
    -0.31
     Verder
    -0.30
     unu
    -0.30
     hara
    -0.30
    numerusform
    -0.29
    POSITIVE LOGITS
     démocr
    1.57
     cérami
    1.51
     stället
    1.45
     réfrig
    1.44
     supérieurs
    1.42
     colorés
    1.41
     varandra
    1.41
     chré
    1.41
     juridiques
    1.41
     jouets
    1.39
    Activations Density 7.739%

    No Known Activations