© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3213
    Prev
    Next
    INDEX
    Explanations

    text related to product warranty and contracts

    oai_token-act-pair · gemini-2.0-flash

    warranty

    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
     Monfieur
    -1.52
     Efq
    -1.48
     Jefus
    -1.46
     myſelf
    -1.42
     purpoſe
    -1.29
     Shakspeare
    -1.27
     houſe
    -1.27
     ſtate
    -1.26
     pleaſure
    -1.24
     Majefty
    -1.23
    POSITIVE LOGITS
     the
    0.84
     The
    0.75
     et
    0.74
     a
    0.73
     in
    0.70
     «
    0.69
     non
    0.68
     Her
    0.68
     
    0.67
     A
    0.66
    Activations Density 1.575%

    No Known Activations