© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10741
    Prev
    Next
    INDEX
    Explanations

    words related to someone dealing with a difficult situation, or requesting permission to do something

    oai_token-act-pair · gemini-2.0-flash

    form handle

    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
     auroit
    -0.72
     olympique
    -0.71
     quæ
    -0.71
     Interceptor
    -0.69
     FBref
    -0.69
     grà
    -0.67
     ſame
    -0.66
     latine
    -0.65
     imprimée
    -0.65
     speedo
    -0.64
    POSITIVE LOGITS
     run
    0.73
     break
    0.65
     roll
    0.65
     drop
    0.64
     visit
    0.62
    ConfigureAwait
    0.61
     change
    0.58
     call
    0.58
     rise
    0.58
     Réponses
    0.57
    Activations Density 2.076%

    No Known Activations