© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6592
    Prev
    Next
    INDEX
    Explanations

    pronouns, conjunctions, words describing government or law, and characters' names, as well as business and office related terms.

    oai_token-act-pair · gemini-2.0-flash

    legal/formal documents

    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
     فريبيس
    -0.60
    PreferredItem
    -0.59
    λίου
    -0.57
     Replay
    -0.56
    GNUC
    -0.55
    raisemb
    -0.54
     replay
    -0.54
    oplayer
    -0.54
    antor
    -0.54
    κτηρισ
    -0.52
    POSITIVE LOGITS
     ab
    1.00
     en
    0.87
     Ab
    0.67
     ProtoMessage
    0.62
    Ab
    0.61
    ab
    0.60
     udaler
    0.60
    sizeCache
    0.56
     abz
    0.50
     honors
    0.49
    Activations Density 6.522%

    No Known Activations