© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    formulas for math calculations

    oai_token-act-pair · gemini-2.0-flash

    math and code

    np_max-act-logits · gemini-2.0-flash

    say "when"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     when
    -3.13
    when
    -2.77
    When
    -2.52
     When
    -2.48
     quando
    -2.41
     cuando
    -2.38
     WHEN
    -2.33
    WHEN
    -2.17
     когда
    -2.08
     lorsqu
    -2.00
    POSITIVE LOGITS
     cherchés
    0.69
    Референце
    0.62
    UnitTesting
    0.59
    期刊论文
    0.57
    tagHelperRunner
    0.55
    tagHelper
    0.52
    <?
    0.52
    évaluateur
    0.51
    UserScript
    0.51
     defaultstate
    0.51
    Activations Density 8.978%

    No Known Activations