© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6888
    Prev
    Next
    INDEX
    Explanations

    code snippets, math formulas, XML-like tags, and software development/programming concepts

    oai_token-act-pair · gemini-2.0-flash

    code and math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     –
    -2.52
     --
    -1.89
     −
    -1.69
     -
    -1.68
     —
    -1.60
     –,
    -1.43
    －
    -1.40
     $-$
    -1.32
     ---
    -1.31
    €“
    -1.28
    POSITIVE LOGITS
    Personendaten
    0.61
    RegressionTest
    0.60
     AppCompatTheme
    0.53
    urcht
    0.53
    CommonModule
    0.53
     Мексичка
    0.51
    dAtA
    0.50
     mengen
    0.50
    SharedCtor
    0.50
    AddHtmlAttribute
    0.49
    Activations Density 3.006%

    No Known Activations