© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12650
    Prev
    Next
    INDEX
    Explanations

    a mix of phrases related to air conditioners, the human body, and a few weakly activated random words

    oai_token-act-pair · gemini-2.0-flash

    Air conditioning or incentives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    expandindo
    -0.86
    #+#
    -0.85
    Спољашње
    -0.82
    脚注の使い方
    -0.79
    reportWebVitals
    -0.77
     Италијани
    -0.77
    NUMX
    -0.73
     autorytatywna
    -0.73
    Vidite
    -0.73
     nahilalakip
    -0.73
    POSITIVE LOGITS
    om
    0.45
    sie
    0.41
    arie
    0.41
    dem
    0.40
    Instance
    0.39
    qrstuvwxyz
    0.38
    ılıyor
    0.38
    tes
    0.38
       
    0.38
     S
    0.38
    Activations Density 0.069%

    No Known Activations