© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3025
    Prev
    Next
    INDEX
    Explanations

    the word "in" in various contexts

    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
    MessageTagHelper
    -0.66
     case
    -0.58
     disparu
    -0.54
     Case
    -0.53
    sibility
    -0.53
    يكب
    -0.52
    ритори
    -0.52
    épendance
    -0.51
     gjelder
    -0.51
    rawdę
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.79
    EndInit
    0.71
    sidemargin
    0.67
    parsedMessage
    0.61
     AssemblyCulture
    0.61
     &___
    0.60
    expandindo
    0.57
    __*/
    0.54
    SOUNDBITE
    0.53
    Portail
    0.52
    Activations Density 1.518%

    No Known Activations