© 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. 3067
    Prev
    Next
    INDEX
    Explanations

    the word "sorry" and related concepts like pardon, problem, and instance (as a single instance of being sorry.)

    oai_token-act-pair · gemini-2.0-flash

    sorry

    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
    Negative Logits
    %")
    -0.78
    eachtet
    -0.74
    randrange
    -0.72
    }\]
    -0.71
    cill
    -0.70
    ]<<"
    -0.69
     AssemblyTitle
    -0.69
    ↩
    -0.69
    ^(@
    -0.68
    ècie
    -0.68
    POSITIVE LOGITS
     odious
    0.60
     luminoso
    0.58
     inactivation
    0.55
     adulta
    0.54
     luminosa
    0.53
    ↵↵
    0.53
     steen
    0.52
    PageContext
    0.52
     informativo
    0.51
     trase
    0.50
    Activations Density 0.792%

    No Known Activations