© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    law and government related documents and terms

    oai_token-act-pair · gemini-2.0-flash

    "in" preposition

    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
    Geplaatst
    -0.68
     ModelExpression
    -0.64
    DockStyle
    -0.63
     purpoſe
    -0.61
     kasarigan
    -0.60
    estacks
    -0.58
    󠁣
    -0.57
    깥
    -0.56
    المكان
    -0.55
    LookAnd
    -0.54
    POSITIVE LOGITS
     in
    1.27
     في
    0.72
    in
    0.69
     în
    0.65
    InThe
    0.65
     в
    0.64
    ใน
    0.64
     در
    0.62
    XmlAccessType
    0.58
    inthe
    0.58
    Activations Density 1.565%

    No Known Activations