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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8313
    Prev
    Next
    INDEX
    Explanations

    the word "responsible."

    oai_token-act-pair · gemini-2.0-flash

    responsible

    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
     responsible
    -1.09
    responsible
    -0.86
     responsibility
    -0.80
     verantwoorde
    -0.80
     Responsibility
    -0.71
     accountable
    -0.69
    Responsible
    -0.69
     responsável
    -0.68
     RESPONS
    -0.68
     responsable
    -0.67
    POSITIVE LOGITS
     obstante
    0.65
    EndContext
    0.65
    poons
    0.65
    enderror
    0.65
    uthor
    0.64
     pédagogique
    0.64
    reza
    0.64
     éditoriale
    0.64
     Goh
    0.64
    rafat
    0.64
    Activations Density 0.607%

    No Known Activations