© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7058
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms, especially those referencing JavaScript and Android.

    oai_token-act-pair · gemini-2.0-flash

    Code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     com
    -1.45
    com
    -1.13
    Com
    -1.05
     Com
    -0.94
     COM
    -0.84
    COM
    -0.84
    coms
    -0.82
     kom
    -0.73
    CppCodeGen
    -0.68
     comm
    -0.66
    POSITIVE LOGITS
    HtmlAttribute
    0.52
    ליט
    0.46
    AuthProvider
    0.45
     primaire
    0.45
    Hulk
    0.45
     BadRequest
    0.44
    kindness
    0.42
     Schmer
    0.42
    iedene
    0.42
     autorité
    0.42
    Activations Density 1.035%

    No Known Activations