© 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. 939
    Prev
    Next
    INDEX
    Explanations

    terms and abbreviations in scientific or technical writing, especially those related to data analysis, physical properties, or medical concepts.

    oai_token-act-pair · gemini-2.0-flash

    say "F" words

    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
    ImageContext
    -0.55
     تانيه
    -0.55
    VersionUID
    -0.53
     Roskov
    -0.53
    CodedInputStream
    -0.52
     MainAxisSize
    -0.52
    AttributeSet
    -0.52
     الاطلاع
    -0.52
     htons
    -0.50
    modelBuilder
    -0.49
    POSITIVE LOGITS
     Facility
    0.73
    Facility
    0.71
    Framework
    0.71
     Flowers
    0.71
     Franch
    0.70
     Formation
    0.70
     Fragment
    0.69
     Facilities
    0.69
    Faculty
    0.69
    Flowers
    0.68
    Activations Density 2.502%

    No Known Activations