© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15307
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets with mathematical symbols and also snippets related to audio signals

    oai_token-act-pair · gemini-2.0-flash

    signal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Pyx
    -0.62
    .
    -0.51
    enumi
    -0.48
    maktadır
    -0.47
    maine
    -0.45
    ylase
    -0.44
     hjemmes
    -0.44
    ↵↵
    -0.44
     informed
    -0.44
    !
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    1.05
     nakalista
    0.96
     resourceCulture
    0.96
    +#+#
    0.88
    MLLoader
    0.85
    AndEndTag
    0.77
     snippetHide
    0.74
     виправивши
    0.74
    RTLD
    0.71
     الحره
    0.70
    Activations Density 10.629%

    No Known Activations