© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5919
    Prev
    Next
    INDEX
    Explanations

    words related to photography and camera settings

    oai_token-act-pair · gemini-2.0-flash

    camera focus/exposure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     photo
    -0.47
     Cataloging
    -0.46
     marge
    -0.44
     Photo
    -0.42
    ParallelGroup
    -0.42
     GENERATED
    -0.42
     circumstantial
    -0.41
     Pineda
    -0.40
     worshipped
    -0.40
    лайн
    -0.40
    POSITIVE LOGITS
     focus
    1.19
     exposure
    1.18
    focus
    1.14
     Exposure
    1.10
    exposure
    1.09
     Focus
    1.05
    Focusing
    1.04
    Focus
    1.03
     focusing
    1.01
     exposures
    0.98
    Activations Density 1.586%

    No Known Activations