© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1568
    Prev
    Next
    INDEX
    Explanations

    words related to photography, specifically depth of field and focus

    oai_token-act-pair · gemini-2.0-flash

    lens and optics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Manager
    -0.41
    DateTimeField
    -0.40
    manager
    -0.39
     manager
    -0.37
     Basu
    -0.37
     Manager
    -0.36
     Fort
    -0.35
    Fort
    -0.35
    mAh
    -0.34
    tedra
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.97
     lens
    0.86
    GEBURTSDATUM
    0.85
     lenses
    0.84
    IsMutable
    0.83
    UnsafeEnabled
    0.78
     Lens
    0.78
     članak
    0.74
     Lenses
    0.74
     optics
    0.74
    Activations Density 1.195%

    No Known Activations