© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5049
    Prev
    Next
    INDEX
    Explanations

    code that uses the term 'image' in combination with transformation operations

    oai_token-act-pair · gemini-2.0-flash

    image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    WriteTagHelper
    -0.64
     Audiodateien
    -0.59
    Obrázky
    -0.58
    setVerticalGroup
    -0.57
    GEBURTSDATUM
    -0.56
     EXERC
    -0.55
    iress
    -0.54
    tede
    -0.54
     bestand
    -0.54
     given
    -0.53
    POSITIVE LOGITS
    DispatchToProps
    0.59
     Réponses
    0.58
     distanciation
    0.57
     auroit
    0.56
     løpet
    0.56
     samarbeid
    0.56
     oublié
    0.56
     dommages
    0.54
     stedet
    0.54
     aukš
    0.54
    Activations Density 11.139%

    No Known Activations