© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    mentions of abstract decision making being performed by humans.

    oai_token-act-pair · gemini-2.0-flash

    authority

    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
     colère
    -0.84
     betrokken
    -0.77
     the
    -0.77
     varandra
    -0.73
     gräns
    -0.71
     scheda
    -0.70
     bakgrund
    -0.69
     déput
    -0.69
     esimer
    -0.69
     vectorielles
    -0.68
    POSITIVE LOGITS
    μη
    0.65
     SIO
    0.63
     atta
    0.62
    else
    0.61
     organisation
    0.60
     Vite
    0.59
     ple
    0.59
     pa
    0.58
     patro
    0.58
    普
    0.57
    Activations Density 3.913%

    No Known Activations