© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5580
    Prev
    Next
    INDEX
    Explanations

    proper nouns corresponding to company, institution, brand and location names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.81
     Efq
    -0.79
     pleaſure
    -0.79
     Jefus
    -0.77
     Theſe
    -0.76
    IndentedString
    -0.75
     ſeveral
    -0.74
     myſelf
    -0.73
     houſe
    -0.71
     itſelf
    -0.71
    POSITIVE LOGITS
     Needs
    0.84
     Has
    0.73
     needs
    0.72
     Gets
    0.66
     Offers
    0.66
     Does
    0.66
     Was
    0.66
     Wants
    0.65
     Uses
    0.65
     Is
    0.62
    Activations Density 4.304%

    No Known Activations