© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5758
    Prev
    Next
    INDEX
    Explanations

    references to lengths of time

    oai_token-act-pair · gemini-2.0-flash

    words indicating time duration

    np_token-act-pair-logits · gpt-4o-mini

    time in the past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     past
    -0.91
    past
    -0.89
     Past
    -0.78
    Past
    -0.78
    過去
    -0.71
     pasado
    -0.70
     PAST
    -0.67
    过去
    -0.65
     passado
    -0.64
     прош
    -0.62
    POSITIVE LOGITS
    LLocation
    0.68
     ag
    0.64
    ثيق
    0.60
    kloped
    0.57
    нциклопе
    0.57
     MainAxisSize
    0.56
    errHandler
    0.56
    SequentialGroup
    0.55
     שוליים
    0.54
    KommentareTeilen
    0.52
    Activations Density 1.414%

    No Known Activations