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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6971
    Prev
    Next
    INDEX
    Explanations

    technical documents related to the internet

    oai_token-act-pair · gemini-2.0-flash

    Disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     utafitiHapana
    -0.50
     plan
    -0.49
     sang
    -0.47
    ́ng
    -0.46
     its
    -0.46
    AddHtmlAttribute
    -0.45
     rub
    -0.44
     тик
    -0.43
     cin
    -0.42
    feira
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.78
    GEBURTSDATUM
    0.74
    ResumeLayout
    0.69
    httphttps
    0.67
    μφωνα
    0.66
     ſmall
    0.61
    Personensuche
    0.61
     متعلقه
    0.61
    ſelves
    0.60
    StoryboardSegue
    0.59
    Activations Density 1.083%

    No Known Activations