© 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. 9026
    Prev
    Next
    INDEX
    Explanations

    named entities in news articles

    oai_token-act-pair · gemini-2.0-flash

    News articles

    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
     earlier
    -1.02
     Earlier
    -0.92
    Earlier
    -0.90
    earlier
    -0.89
     Late
    -0.75
    Late
    -0.74
    WEDNESDAY
    -0.66
    FRIDAY
    -0.65
     late
    -0.64
    THURSDAY
    -0.64
    POSITIVE LOGITS
     Marquette
    0.65
    netinet
    0.61
    MessageOf
    0.60
     Armin
    0.60
     InputDecoration
    0.59
     vôtre
    0.59
     enfans
    0.58
     juridiques
    0.57
    WillAppear
    0.57
    Obrázky
    0.57
    Activations Density 15.180%

    No Known Activations