© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    food ingredients and recipes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     intptr
    -0.60
    Referències
    -0.60
     विश्वसनीयता
    -0.54
     Roskov
    -0.50
    říklad
    -0.49
    Ser
    -0.47
    englanniksi
    -0.47
     }}}
    -0.47
    ser
    -0.47
    次代
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.56
    viewDidLoad
    0.54
     насељу
    0.54
     insuffisamment
    0.53
     ItemStack
    0.52
    hagic
    0.51
    SPATH
    0.51
    rxjs
    0.50
    ächt
    0.50
    
    0.50
    Activations Density 2.441%

    No Known Activations