© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    descriptions of timekeeping devices

    oai_token-act-pair · gemini-2.0-flash

    mechanical

    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
     EdgeInsets
    -0.70
    FXMLLoader
    -0.56
    ceedings
    -0.52
    قایناقلار
    -0.52
    routeProvider
    -0.52
    ]")]
    -0.51
    րջ
    -0.49
     menurun
    -0.48
     اطلع
    -0.48
     úč
    -0.47
    POSITIVE LOGITS
    Gön
    0.67
    GRect
    0.63
    ]--;
    0.60
    IsContent
    0.59
    AndroidJUnit
    0.57
    Vidite
    0.57
    findpost
    0.57
     utafitiHapana
    0.56
    μιουργ
    0.55
     sundown
    0.55
    Activations Density 0.137%

    No Known Activations