© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7189
    Prev
    Next
    INDEX
    Explanations

    descriptions of negative consequences and problems

    oai_token-act-pair · gemini-2.0-flash

    productivity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     geslacht
    -0.66
     esternos
    -0.54
     téléphonique
    -0.54
    lectricité
    -0.51
     Gespräche
    -0.50
    MessageTagHelper
    -0.50
     ligar
    -0.49
     MICH
    -0.49
    sierra
    -0.49
    égard
    -0.49
    POSITIVE LOGITS
     productivity
    1.53
    productivity
    1.23
     Productivity
    1.22
    Productivity
    1.15
     productive
    1.14
     efficiency
    1.13
     producti
    1.07
     productividad
    0.99
     production
    0.98
    productive
    0.97
    Activations Density 0.923%

    No Known Activations