© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML-like markup

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    ADRID
    -0.48
    REQUENCY
    -0.44
     отношению
    -0.40
    ADORA
    -0.39
    ÁND
    -0.39
    HICLE
    -0.39
    FORMAN
    -0.38
    ATUS
    -0.37
    QUENCE
    -0.37
    FORMANCE
    -0.35
    POSITIVE LOGITS
     AspNetCore
    0.89
    InputBorder
    0.83
    GEBURTSDATUM
    0.81
    webElementXpaths
    0.75
     Chwiliwch
    0.74
     unknownFields
    0.74
     Assignee
    0.73
     Wikimedijinoj
    0.72
    цездатний
    0.71
     ProtoMessage
    0.71
    Activations Density 11.944%

    No Known Activations