© 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. 14358
    Prev
    Next
    INDEX
    Explanations

    the unit of measurement "feet" and the word "office", possibly looking for spatial descriptions or references to organizations

    oai_token-act-pair · gemini-2.0-flash

    real estate / buildings

    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
    ".
    -0.79
     يتيمه
    -0.78
    XmlAccessorType
    -0.71
    دانشنامهٔ
    -0.69
    :✨
    -0.69
    ectoria
    -0.68
    تقاوى
    -0.66
     ***/
    -0.66
    SequentialGroup
    -0.66
    Portail
    -0.65
    POSITIVE LOGITS
    “
    0.62
    theria
    0.53
     Popularity
    0.50
    …
    0.50
     –
    0.49
     bruto
    0.48
     consumers
    0.48
    uarts
    0.48
    ishw
    0.47
    ณ์
    0.47
    Activations Density 0.131%

    No Known Activations