© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    words related to time passing and verbs describing observing events

    oai_token-act-pair · gemini-2.0-flash

    time passed

    np_max-act · gemini-2.0-flash

    spent

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    
    -0.75
    clusal
    -0.64
     HasFactory
    -0.63
    THESIS
    -0.62
     ModelExpression
    -0.60
     <=",
    -0.60
    igshid
    -0.59
     vervol
    -0.58
    ostante
    -0.57
    ähig
    -0.57
    POSITIVE LOGITS
    <bos>
    0.79
    webElement
    0.56
    TagMode
    0.52
    Распо
    0.48
     cdti
    0.47
    tamp
    0.47
     FetchType
    0.47
    rawDesc
    0.46
    Pairs
    0.46
    Rudy
    0.45
    Activations Density 2.449%

    No Known Activations