© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4187
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to strong opinions or complex situations involving problem-solving, emotions and interpersonal interactions.

    oai_token-act-pair · gemini-2.0-flash

    pride

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -1.30
     bezeichneter
    -1.27
     nakalista
    -1.23
     Monfieur
    -1.19
    RenderAtEndOf
    -1.16
     Majefty
    -1.15
     الحره
    -1.15
     himſelf
    -1.14
     myſelf
    -1.14
     itſelf
    -1.13
    POSITIVE LOGITS
     
    0.65
      
    0.62
     on
    0.57
    ↵
    0.56
     u
    0.55
    .
    0.54
    ↵↵
    0.53
     U
    0.50
     is
    0.50
    ;
    0.50
    Activations Density 13.265%

    No Known Activations