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. 1173
    Prev
    Next
    INDEX
    Explanations

    text about the mechanics and operation of a Linotype machine and typesetting

    oai_token-act-pair · gemini-2.0-flash

    printing type

    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
    ſelf
    -0.82
    ^(@)
    -0.82
     myſelf
    -0.75
     Majefty
    -0.73
     photolibrary
    -0.72
     faſt
    -0.71
     Jefus
    -0.69
     Theſe
    -0.68
     Anſ
    -0.67
     purpoſe
    -0.67
    POSITIVE LOGITS
    box
    0.56
    aarrggbb
    0.54
    AsUp
    0.53
    ագրություններ
    0.53
    po
    0.53
    <bos>
    0.52
     الاطلاع
    0.51
     background
    0.51
    us
    0.49
    ad
    0.49
    Activations Density 3.784%

    No Known Activations