Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1103
    Prev
    Next
    INDEX
    Explanations

    time remaining or time until

    oai_token-act-pair · gemini-2.0-flash

    left

    np_token-act-pair-logits · gemini-2.0-flash

    Time remaining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    adpleegd
    -0.59
    MessageOf
    -0.58
    (!__
    -0.54
    يميديا
    -0.53
    }'
    -0.46
    ViewImports
    -0.45
    //----
    -0.44
    UnusedPrivate
    -0.44
    TextChanged
    -0.43
     Lan
    -0.43
    POSITIVE LOGITS
     leſs
    0.89
     myſelf
    0.87
     houſe
    0.84
     ſeveral
    0.83
     pleaſure
    0.81
     Jefus
    0.79
     poffe
    0.79
     Majefty
    0.77
     purpoſe
    0.74
     Efq
    0.73
    Activations Density 1.215%

    No Known Activations