© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10389
    Prev
    Next
    INDEX
    Explanations

    references to images or visual depictions

    oai_token-act-pair · gemini-2.0-flash

    pictures / photos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     photos
    -1.05
     PHOTOS
    -0.95
     Photos
    -0.94
     photo
    -0.92
     pictures
    -0.88
    PHOTOS
    -0.86
    Photos
    -0.86
    photos
    -0.84
     foto
    -0.83
     사진
    -0.82
    POSITIVE LOGITS
    estacks
    0.60
    <bos>
    0.60
    TabIndex
    0.59
    FragmentManager
    0.49
     Parce
    0.49
     Empire
    0.48
     coffret
    0.48
     Daß
    0.47
     animato
    0.47
    InjectAttribute
    0.47
    Activations Density 7.045%

    No Known Activations