© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11330
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and technical writing, especially markers of importance.

    oai_token-act-pair · gemini-2.0-flash

    technical papers

    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
     prec
    -0.51
     verwijzen
    -0.50
     ongles
    -0.50
     Venue
    -0.48
    注明
    -0.47
    fır
    -0.47
    ptonshire
    -0.46
     altrimenti
    -0.46
    copy
    -0.45
    kmale
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.97
    Autoritní
    0.61
     protoimpl
    0.59
    Източници
    0.58
    tagHelperRunner
    0.57
    InitVars
    0.57
    InjectAttribute
    0.56
    PickerController
    0.56
    hObject
    0.55
    fVar
    0.54
    Activations Density 0.912%

    No Known Activations