© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5836
    Prev
    Next
    INDEX
    Explanations

    uses of the word "made" to describe physical objects

    oai_token-act-pair · gemini-2.0-flash

    material composition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    made
    -1.10
     made
    -1.06
     Made
    -1.04
    Made
    -1.01
     MADE
    -0.99
    MADE
    -0.94
     composed
    -0.77
    composed
    -0.76
     constituted
    -0.72
     Composed
    -0.67
    POSITIVE LOGITS
     of
    0.83
     FetchType
    0.59
    Источник
    0.54
    quale
    0.53
    rawDesc
    0.51
     defStyleAttr
    0.50
    tableFuture
    0.49
    springframework
    0.48
    CURLOPT
    0.46
    ించ
    0.46
    Activations Density 0.756%

    No Known Activations