© 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. 11915
    Prev
    Next
    INDEX
    Explanations

    date and time formats, as well as the fragment "org"

    oai_token-act-pair · gemini-2.0-flash

    Dates and times

    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
    queryInterface
    -0.54
     slip
    -0.48
    are
    -0.43
     reef
    -0.43
    ঝ
    -0.43
     torn
    -0.41
     enjoying
    -0.41
     slipping
    -0.41
    of
    -0.40
    react
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.78
    EDEFAULT
    0.78
    ContentAsync
    0.78
    WriteBarrier
    0.72
     estekak
    0.71
    migrationBuilder
    0.69
     архивлан
    0.69
     GenerationType
    0.68
    AnimationsModule
    0.68
    ParallelGroup
    0.67
    Activations Density 13.362%

    No Known Activations