© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12374
    Prev
    Next
    INDEX
    Explanations

    HTML code for radio button form entries

    oai_token-act-pair · gemini-2.0-flash

    item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     '\\;'
    -0.66
     <=",
    -0.64
    kloped
    -0.62
    CloseOperation
    -0.62
    aarrggbb
    -0.61
     CreateTagHelper
    -0.57
    CppMethod
    -0.57
     physique
    -0.56
    ViewImports
    -0.54
     undersigned
    -0.54
    POSITIVE LOGITS
    Ahoj
    0.64
    hæng
    0.63
    tahankan
    0.62
    timbangkan
    0.61
     nhàng
    0.59
     Corintios
    0.58
    ]))
    0.58
    rivit
    0.57
    AddWithValue
    0.57
    urangan
    0.57
    Activations Density 2.007%

    No Known Activations