© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12678
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially countries and cities, within a news context, frequently emphasizing "the" before a location.

    oai_token-act-pair · gemini-2.0-flash

    geographic, political entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GEBURTSDATUM
    -0.90
    enumii
    -0.83
    BeginContext
    -0.74
     оригіналу
    -0.73
    CodedInputStream
    -0.65
    ьаж
    -0.63
    ]")]
    -0.61
    enumi
    -0.59
     跳转至
    -0.59
    oa̍t
    -0.58
    POSITIVE LOGITS
    AnchorStyles
    0.65
    łaś
    0.54
     للمعارف
    0.51
     ria
    0.48
     sockaddr
    0.47
     htmlFor
    0.46
    います
    0.46
     Infine
    0.46
    bní
    0.46
     Travelers
    0.45
    Activations Density 1.603%

    No Known Activations