© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12202
    Prev
    Next
    INDEX
    Explanations

    phrases with "come on" and, separately, phrases requesting help

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -0.82
    UnusedPrivate
    -0.80
     snippetHide
    -0.80
     Majefty
    -0.79
     contextLoads
    -0.77
     Theſe
    -0.76
    LEncoder
    -0.75
     ―――――
    -0.73
     propOrder
    -0.73
    GEBURTS
    -0.71
    POSITIVE LOGITS
     please
    0.57
     Please
    0.52
    Please
    0.50
    不如
    0.48
    <bos>
    0.48
     aventura
    0.47
    '
    0.45
     let
    0.45
     lets
    0.45
     now
    0.45
    Activations Density 0.804%

    No Known Activations