© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8602
    Prev
    Next
    INDEX
    Explanations

    the word "of" followed by capitalized words, especially acronyms like "GCTF".

    oai_token-act-pair · gemini-2.0-flash

    member

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ddelweddau
    -0.74
    ArrowToggle
    -0.73
     ProtoMessage
    -0.70
    CppMethod
    -0.69
    AndEndTag
    -0.69
    GEBURTSDATUM
    -0.68
    /*---
    -0.64
    RegistryLite
    -0.64
    ьаж
    -0.63
     Waray
    -0.63
    POSITIVE LOGITS
     member
    1.80
     Member
    1.54
    Member
    1.48
    member
    1.46
     MEMBER
    1.37
    MEMBER
    1.13
     Mitglied
    1.13
     miembro
    0.96
     membro
    0.84
     membre
    0.84
    Activations Density 2.903%

    No Known Activations