© 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. 5368
    Prev
    Next
    INDEX
    Explanations

    image manipulation or processing

    oai_token-act-pair · gemini-2.0-flash

    image aspect ratio

    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
    Personendaten
    -0.83
     houſe
    -0.78
     Monfieur
    -0.77
    ſelves
    -0.77
    ſelf
    -0.75
     ſte
    -0.70
     himſelf
    -0.70
     themſelves
    -0.70
     Jefus
    -0.70
     ſtate
    -0.69
    POSITIVE LOGITS
     aspect
    0.71
    AspectRatio
    0.68
     fit
    0.65
    fit
    0.64
     Fit
    0.59
    aspect
    0.58
     FIT
    0.57
     stretch
    0.57
     stretched
    0.55
     crop
    0.54
    Activations Density 0.942%

    No Known Activations