© 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. 12977
    Prev
    Next
    INDEX
    Explanations

    text between forward slashes

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     autorytatywna
    -0.87
     kasarigan
    -0.83
    SharedCtor
    -0.79
    InputBorder
    -0.77
    :✨
    -0.77
     Reverso
    -0.77
     AssemblyCulture
    -0.76
    localctx
    -0.74
    Biographie
    -0.72
     Numerade
    -0.72
    POSITIVE LOGITS
     via
    0.53
     his
    0.47
    quem
    0.47
     some
    0.45
     the
    0.44
     себе
    0.43
     himself
    0.42
    dieren
    0.42
    </s>
    0.42
     r
    0.41
    Activations Density 6.708%

    No Known Activations