© 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. 7939
    Prev
    Next
    INDEX
    Explanations

    references to specific times, dates, and nights, especially in legal testimony

    oai_token-act-pair · gemini-2.0-flash

    time of day

    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
    RegressionTest
    -0.75
     viewType
    -0.65
     protoimpl
    -0.63
    __':
    -0.60
    ждане
    -0.59
    LabelTagHelper
    -0.59
     himo
    -0.59
     intStringLen
    -0.59
    __":
    -0.57
    AutoScale
    -0.57
    POSITIVE LOGITS
     weekly
    0.54
     daily
    0.53
    IntoConstraints
    0.49
     }}"></
    0.48
    StateException
    0.48
    PTI
    0.46
     evening
    0.45
    vably
    0.44
     fortnight
    0.44
    yar
    0.43
    Activations Density 6.407%

    No Known Activations