© 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. 14533
    Prev
    Next
    INDEX
    Explanations

    proper nouns and adjectives with a corporate, educational, governmental, or legal flavor, often referring to events such as awards, announcements, ceremonies, or sessions.

    oai_token-act-pair · gemini-2.0-flash

    earlier

    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
     Last
    -1.07
    Last
    -1.05
     last
    -1.05
    last
    -0.94
     LAST
    -0.91
    LAST
    -0.87
     this
    -0.83
     dernière
    -0.76
     viime
    -0.76
     última
    -0.72
    POSITIVE LOGITS
     earlier
    2.09
     Earlier
    2.02
    earlier
    1.97
    Earlier
    1.95
     sooner
    1.08
     EARL
    0.92
     younger
    0.73
     wcześ
    0.71
     eerder
    0.71
     wcześniej
    0.68
    Activations Density 9.234%

    No Known Activations