© 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. 5862
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or code-related terminology, along with some Spanish words.

    oai_token-act-pair · gemini-2.0-flash

    Technical issues and multiple languages

    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
     ticket
    -0.95
    ticket
    -0.85
     tickets
    -0.85
    Ticket
    -0.79
     Ticket
    -0.77
     TICKET
    -0.77
     Tickets
    -0.74
    TICKET
    -0.74
     TICKETS
    -0.71
     ticketing
    -0.71
    POSITIVE LOGITS
    makeConstraints
    0.62
    RTLR
    0.58
    coch
    0.56
     yyr
    0.54
    TagMode
    0.54
    GIVEREF
    0.52
    Varint
    0.50
     unknownFields
    0.50
    Rhestr
    0.49
    UIControlState
    0.48
    Activations Density 0.684%

    No Known Activations