© 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. 884
    Prev
    Next
    INDEX
    Explanations

    medical measurements, especially those including numbers and units like "mM", "pM", "cm", "+/-", and "sec"

    oai_token-act-pair · gemini-2.0-flash

    Numbers, symbols, and foreign language

    np_max-act-logits · gemini-2.0-flash

    accented characters

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     α
    -0.80
     β
    -0.79
     Ō
    -0.77
     Māori
    -0.76
     Mā
    -0.75
     Pokémon
    -0.75
     Atlético
    -0.75
     résumé
    -0.74
     García
    -0.73
     θ
    -0.72
    POSITIVE LOGITS
    ẫy
    0.35
    ậm
    0.34
     wasnt
    0.33
    ấc
    0.32
    ướt
    0.32
     doesnt
    0.32
     didnt
    0.31
     оригіналу
    0.30
    Према
    0.30
    ứt
    0.30
    Activations Density 20.669%

    No Known Activations