© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5102
    Prev
    Next
    INDEX
    Explanations

    syllables that might form parts of names, especially non-English ones

    oai_token-act-pair · gemini-2.0-flash

    Code, errors, documentation

    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
     Мексичка
    -0.53
     Frankfort
    -0.52
     STM
    -0.47
    libft
    -0.47
     للمعارف
    -0.46
     تانيه
    -0.45
    idopsis
    -0.43
    hysema
    -0.43
    AddHtmlAttribute
    -0.42
    TestingModule
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.53
    ällor
    0.51
    DeleteBehavior
    0.49
     danni
    0.49
    ved
    0.48
     muri
    0.47
     wajib
    0.47
     vœux
    0.47
     yako
    0.46
    setMode
    0.46
    Activations Density 0.675%

    No Known Activations