© 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. 360
    Prev
    Next
    INDEX
    Explanations

    mentions of periods of time using the word "for"

    oai_token-act-pair · gemini-2.0-flash

    for

    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
     Almost
    -0.67
    Almost
    -0.64
     Nearly
    -0.61
    almost
    -0.59
     quase
    -0.57
     hampir
    -0.56
    Nearly
    -0.56
     casi
    -0.52
    nearly
    -0.52
     almost
    -0.50
    POSITIVE LOGITS
     pinulongan
    1.08
    Geplaatst
    0.93
     myſelf
    0.88
     Efq
    0.86
     raiſ
    0.85
     itſelf
    0.84
    MigrationBuilder
    0.78
     pleaſure
    0.78
     للاسماء
    0.77
    ArgsConstructor
    0.75
    Activations Density 10.387%

    No Known Activations