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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7328
    Prev
    Next
    INDEX
    Explanations

    the last name "Hardy", with some tolerance for typos

    oai_token-act-pair · gemini-2.0-flash

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.35
     itſelf
    -1.16
     chofe
    -1.09
     Jefus
    -1.09
     myſelf
    -1.08
     houſe
    -0.98
     fhew
    -0.96
     whoſe
    -0.96
     Anſ
    -0.95
     Houſe
    -0.95
    POSITIVE LOGITS
    <eos>
    0.58
     Ho
    0.52
     me
    0.52
    ↵
    0.51
     the
    0.51
    -
    0.50
     do
    0.50
     here
    0.50
    '
    0.50
     Do
    0.49
    Activations Density 2.325%

    No Known Activations