© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14774
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to construction and renovation projects

    oai_token-act-pair · gemini-2.0-flash

    repair/improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    flashdata
    -0.49
    ishman
    -0.49
    MessageOf
    -0.48
     générales
    -0.48
    issantes
    -0.47
    edas
    -0.47
    peria
    -0.46
    )^{-
    -0.46
    ::::::::
    -0.45
     menac
    -0.44
    POSITIVE LOGITS
     AssemblyProduct
    0.77
    Portale
    0.71
     myſelf
    0.66
    AnimationsModule
    0.63
     herself
    0.60
     houſe
    0.59
     незавершена
    0.57
     itſelf
    0.57
    存于互联网档案馆
    0.57
    Hozzáférés
    0.57
    Activations Density 0.383%

    No Known Activations