© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5994
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words and names of people and places

    oai_token-act-pair · gemini-2.0-flash

    av

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     дописавши
    -0.83
    GEBURTSDATUM
    -0.81
    Билгалдахарш
    -0.76
     mergeFrom
    -0.76
    хьтан
    -0.75
     nahilalakip
    -0.72
    الحياه
    -0.71
    oa̍t
    -0.64
    Rohy
    -0.64
    '}>
    -0.63
    POSITIVE LOGITS
    äj
    0.63
    örté
    0.56
     Escor
    0.55
    StackNavigator
    0.54
     répon
    0.53
    綽
    0.52
     ſta
    0.51
    ாய
    0.51
    ęp
    0.50
    꼈
    0.50
    Activations Density 0.067%

    No Known Activations