© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10417
    Prev
    Next
    INDEX
    Explanations

    words related to time, specifically weeks and years, and future plans

    oai_token-act-pair · gemini-2.0-flash

    week or year

    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
     vicenda
    -0.54
    Наводи
    -0.51
    nosotros
    -0.49
     cérami
    -0.48
     vícti
    -0.48
    ulement
    -0.47
    躇
    -0.47
     kasarigan
    -0.47
     povezave
    -0.47
    ñora
    -0.47
    POSITIVE LOGITS
     estekak
    0.69
    rawDesc
    0.62
    րջ
    0.61
    MetaObject
    0.60
     protoimpl
    0.60
    EDEFAULT
    0.60
    ########.
    0.60
    脚注の使い方
    0.59
    OGND
    0.56
    omitempty
    0.56
    Activations Density 10.705%

    No Known Activations