© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    words or phrases that specify a time or date

    oai_token-act-pair · gemini-2.0-flash

    time periods

    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
     before
    -2.34
    before
    -2.31
     Before
    -2.19
    Before
    -2.14
     BEFORE
    -2.03
     after
    -1.99
    after
    -1.97
    BEFORE
    -1.88
     After
    -1.84
    After
    -1.84
    POSITIVE LOGITS
     Vikipedi
    0.57
    AddHtmlAttribute
    0.56
    shund
    0.54
    addGap
    0.52
    PRWEB
    0.51
    noons
    0.51
    Referensi
    0.49
    RouterModule
    0.48
    клопе
    0.48
    ScopeManager
    0.48
    Activations Density 9.231%

    No Known Activations