© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1928
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions, especially those containing dollar signs and exponents

    oai_token-act-pair · gemini-2.0-flash

    Code / math fragments

    np_max-act-logits · gemini-2.0-flash

    digits

    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
     autorytatywna
    -0.62
     Efq
    -0.61
     дописавши
    -0.59
    ấc
    -0.59
     ſeveral
    -0.57
    ợn
    -0.57
    ẫy
    -0.57
     Chrift
    -0.56
    unteers
    -0.55
    ()")
    -0.55
    POSITIVE LOGITS
    ContentAlignment
    0.56
    có
    0.49
    âm
    0.49
    khó
    0.48
    kho
    0.48
     preuves
    0.47
    =$
    0.47
     abbiano
    0.47
    $\
    0.47
    ViewChild
    0.47
    Activations Density 38.011%

    No Known Activations