© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10979
    Prev
    Next
    INDEX
    Explanations

    strings from code and math equations

    oai_token-act-pair · gemini-2.0-flash

    fn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     wikipagina
    -0.76
    DockStyle
    -0.75
     الحره
    -0.73
    harapkan
    -0.71
    Descriere
    -0.69
     Palgrave
    -0.69
    RuleContext
    -0.66
     näky
    -0.65
     arşivlendi
    -0.65
     StatelessWidget
    -0.65
    POSITIVE LOGITS
    en
    1.04
    n
    1.02
    nen
    0.96
    jan
    0.94
    nan
    0.92
    ien
    0.89
    van
    0.87
    ن
    0.87
    nnnn
    0.85
    hen
    0.85
    Activations Density 3.225%

    No Known Activations