© 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. 887
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology as well as some possible names, especially if they are associated with legal or medical contexts.

    oai_token-act-pair · gemini-2.0-flash

    the letter L

    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
     '\\;'
    -0.57
    intios
    -0.55
     kasarigan
    -0.53
     للاسماء
    -0.52
     estimés
    -0.52
     ویکی‌پدیای
    -0.48
    abestanden
    -0.46
    )_/¯
    -0.43
    huriyet
    -0.43
     مشين
    -0.42
    POSITIVE LOGITS
     L
    1.30
    L
    1.20
     Ll
    1.16
     LL
    1.16
     LH
    1.11
     LO
    1.10
     Ls
    1.09
     LR
    1.09
     LN
    1.08
     Lo
    1.07
    Activations Density 13.133%

    No Known Activations