© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14715
    Prev
    Next
    INDEX
    Explanations

    the word "in" and "on" followed by months or time references

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    __).
    -0.66
     order
    -0.55
    Portale
    -0.51
    Portail
    -0.49
     exchange
    -0.48
    ("$.
    -0.47
    getBean
    -0.47
     recommandée
    -0.47
    ณฑ
    -0.47
    scalatest
    -0.47
    POSITIVE LOGITS
     transférez
    0.55
    المل
    0.52
    原始内容存档于
    0.50
     store
    0.49
     surla
    0.49
     Wicidata
    0.47
    hésite
    0.47
    process
    0.47
    тності
    0.47
    曖昧さ回避
    0.47
    Activations Density 2.715%

    No Known Activations