© 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. 3742
    Prev
    Next
    INDEX
    Explanations

    words related to official documents, like the kind needed for international travel

    oai_token-act-pair · gemini-2.0-flash

    travel 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
    SharedCtor
    -0.77
    Източници
    -0.62
    Референце
    -0.59
     Drapeau
    -0.57
     ComVisible
    -0.56
    GeneratedCode
    -0.56
     متعلقه
    -0.56
    sizeCache
    -0.55
    Pautan
    -0.55
    Šaltiniai
    -0.54
    POSITIVE LOGITS
     تانيه
    0.57
     MainAxisSize
    0.55
    ConstraintMaker
    0.52
     springfox
    0.52
    tagHelperRunner
    0.51
    rshire
    0.50
     BnF
    0.50
     CreateTagHelper
    0.49
    ModelSerializer
    0.48
    EndProject
    0.48
    Activations Density 0.650%

    No Known Activations