© 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. 16210
    Prev
    Next
    INDEX
    Explanations

    the word "in" preceded or followed by certain other words

    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
    kháu
    -0.55
     contrasted
    -0.52
    RegistryLite
    -0.50
     RIPRODUZIONE
    -0.49
    참고
    -0.48
    TintMode
    -0.47
    TProtocol
    -0.46
     SIMBAD
    -0.46
    IBar
    -0.46
    مانية
    -0.46
    POSITIVE LOGITS
     in
    0.84
     concert
    0.71
     con
    0.66
     association
    0.64
    conj
    0.63
     conjun
    0.63
     conj
    0.59
     CreateTagHelper
    0.59
     σε
    0.57
    association
    0.56
    Activations Density 1.415%

    No Known Activations