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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10379
    Prev
    Next
    INDEX
    Explanations

    date formats and the use of APIs, classes and models with Bluetooth, cables and connectivity

    oai_token-act-pair · gemini-2.0-flash

    research/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     myſelf
    -0.91
     itſelf
    -0.90
     Efq
    -0.87
     fevere
    -0.87
     nahilalakip
    -0.86
     Theſe
    -0.86
     Chriftian
    -0.85
     Monfieur
    -0.85
     himſelf
    -0.84
     becauſe
    -0.84
    POSITIVE LOGITS
     (
    0.53
     i
    0.50
     and
    0.47
    -
    0.47
     best
    0.46
     u
    0.45
     an
    0.44
     «
    0.44
     –
    0.43
     of
    0.43
    Activations Density 0.474%

    No Known Activations