© 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. 5807
    Prev
    Next
    INDEX
    Explanations

    sports related awards and mentions of high school and college

    oai_token-act-pair · gemini-2.0-flash

    Awards

    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
     kasarigan
    -0.68
    trup
    -0.64
     Audiodateien
    -0.61
     wikipagina
    -0.61
     crossorigin
    -0.59
     MonoBehaviour
    -0.58
    Tembelea
    -0.58
    囗
    -0.58
    abestanden
    -0.57
     Caldwell
    -0.57
    POSITIVE LOGITS
     Estonian
    0.39
     getchar
    0.38
     Yea
    0.38
     Theſe
    0.38
     
    0.38
    =$?
    0.37
     Czechoslovak
    0.36
     YA
    0.36
     EAC
    0.36
    WillAppear
    0.35
    Activations Density 6.914%

    No Known Activations