© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and activities or events within them.

    oai_token-act-pair · gemini-2.0-flash

    place

    np_max-act-logits · gemini-2.0-flash

    references to 'place'

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     place
    -0.68
     tre
    -0.59
     space
    -0.50
     chance
    -0.47
     work
    -0.46
    蚪
    -0.45
     enter
    -0.44
     maka
    -0.44
    mut
    -0.44
    ilers
    -0.44
    POSITIVE LOGITS
     avoient
    0.71
     feroit
    0.69
     étoient
    0.65
     figliu
    0.65
     gratuitement
    0.64
     enfans
    0.64
     alugar
    0.63
    endphp
    0.63
     polaire
    0.62
    ValueStyle
    0.60
    Activations Density 4.494%

    No Known Activations