© 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. 6549
    Prev
    Next
    INDEX
    Explanations

    sentences containing the words "we" and "would."

    oai_token-act-pair · gemini-2.0-flash

    Web-related words

    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
     expected
    -2.30
    expected
    -2.19
     Expected
    -2.03
    Expected
    -1.88
     hoped
    -1.88
     anticipated
    -1.62
     EXPECT
    -1.55
     expectation
    -1.45
     esperaba
    -1.45
    EXPECTED
    -1.43
    POSITIVE LOGITS
    httphttps
    0.78
    ]--;
    0.63
    ngdoc
    0.60
     Autorizaciones
    0.58
    Tembelea
    0.57
    ulose
    0.56
     Paglinawan
    0.55
    cdnjs
    0.54
    ündig
    0.53
    newpage
    0.51
    Activations Density 3.330%

    No Known Activations