© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10546
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time

    oai_token-act-pair · gemini-2.0-flash

    Passage of time

    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
     nahilalakip
    -1.16
    RenderAtEndOf
    -1.15
     Normdatei
    -1.10
     Roskov
    -1.08
     Majefty
    -1.00
    GEBURTSDATUM
    -0.98
     myſelf
    -0.98
    ContentAsync
    -0.97
     Monfieur
    -0.97
    setVerticalGroup
    -0.94
    POSITIVE LOGITS
     past
    0.48
     
    0.41
     hands
    0.40
     tố
    0.40
     taken
    0.39
    客
    0.38
    .
    0.38
     O
    0.36
     majd
    0.36
     in
    0.36
    Activations Density 1.832%

    No Known Activations