© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13767
    Prev
    Next
    INDEX
    Explanations

    the word "in" when used as a preposition

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     especially
    -0.83
     Especially
    -0.79
    especially
    -0.75
    Especially
    -0.73
     especialmente
    -0.65
     specialmente
    -0.64
     principalmente
    -0.62
     terutama
    -0.60
    specially
    -0.59
    pecially
    -0.59
    POSITIVE LOGITS
     particular
    1.60
    particular
    1.30
     addition
    1.05
     particolare
    0.99
     Particular
    0.96
    Particular
    0.88
     fact
    0.84
     turn
    0.83
     PARTICULAR
    0.77
    addition
    0.77
    Activations Density 5.617%

    No Known Activations