© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    the word "over", especially when followed by a time period like "the years."

    oai_token-act-pair · gemini-2.0-flash

    Over

    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
    pitaux
    -0.59
    TintMode
    -0.54
    idopsis
    -0.53
     insuffisamment
    -0.51
    PreferredItem
    -0.50
    TagMode
    -0.50
     dafür
    -0.50
    RTCF
    -0.50
     oprot
    -0.48
     getItemId
    -0.47
    POSITIVE LOGITS
     the
    0.54
    multiple
    0.54
     multiple
    0.52
    NgModule
    0.52
    TestBed
    0.52
    Населення
    0.49
    incomplete
    0.47
     Teufel
    0.47
     spells
    0.45
    fag
    0.45
    Activations Density 0.456%

    No Known Activations