© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5515
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes about eating food and restaurants

    oai_token-act-pair · gemini-2.0-flash

    Non-English 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    expandindo
    -0.49
     <",
    -0.48
     casting
    -0.47
    BeginContext
    -0.45
    écrire
    -0.45
     toegang
    -0.44
    étit
    -0.41
    جغرافيا
    -0.40
    endforeach
    -0.40
     Pollutant
    -0.39
    POSITIVE LOGITS
     disambiguazione
    0.74
    مصادر
    0.71
    ніципа
    0.69
    ThroughAttribute
    0.68
    脚注の使い方
    0.68
     Wiktionnaire
    0.64
     تعدى
    0.62
     通販
    0.59
    SPJ
    0.58
    তথ্যসূত্র
    0.58
    Activations Density 1.328%

    No Known Activations