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. 7221
    Prev
    Next
    INDEX
    Explanations

    the word "ready"

    oai_token-act-pair · gemini-2.0-flash

    ready

    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
     “
    -0.67
     he
    -0.66
     sa
    -0.66
     Us
    -0.64
     us
    -0.63
     c
    -0.63
     a
    -0.62
     
    -0.62
     cer
    -0.61
     por
    -0.60
    POSITIVE LOGITS
     Monfieur
    1.13
     Reſ
    1.09
     pleaſure
    1.01
     Shakspeare
    0.98
     myſelf
    0.93
     Houſe
    0.92
     Moslem
    0.92
     Shaksp
    0.92
     Cæsar
    0.91
     Eſ
    0.91
    Activations Density 2.720%

    No Known Activations