© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14976
    Prev
    Next
    INDEX
    Explanations

    the word "place" or words appearing near "place"

    oai_token-act-pair · gemini-2.0-flash

    place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    دانشنامهٔ
    -1.04
    >--}}
    -0.84
     المعيارى
    -0.79
    ViewFeatures
    -0.79
    placed
    -0.77
     placing
    -0.76
    endwhile
    -0.74
     سكانية
    -0.74
     }}$}
    -0.73
    rachtet
    -0.72
    POSITIVE LOGITS
     ones
    0.57
    '
    0.52
    WireFormatLite
    0.51
    <bos>
    0.45
    How
    0.45
    Where
    0.45
    man
    0.43
    twimg
    0.43
    od
    0.42
    のは
    0.42
    Activations Density 0.214%

    No Known Activations