© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15431
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by a noun or noun phrase

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     Majefty
    -0.72
    ConverterFactory
    -0.70
     Diſ
    -0.66
     pleaſure
    -0.66
     fhould
    -0.66
     Cæsar
    -0.66
     IBOutlet
    -0.66
    Tikang
    -0.65
    ỡng
    -0.65
     perfons
    -0.65
    POSITIVE LOGITS
     disambiguazione
    0.66
     autorytatywna
    0.58
     resourceCulture
    0.54
    Datuak
    0.52
     mé
    0.51
     nonatomic
    0.51
     typelib
    0.48
     الحره
    0.47
     li
    0.47
     ujednoznacz
    0.46
    Activations Density 0.569%

    No Known Activations