© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    terms related to language and communication, including specific languages and slang terms

    oai_token-act-pair · gemini-2.0-flash

    discussing text or code

    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
    EntityFramework
    -0.54
    BoxShadow
    -0.51
    DeleteBehavior
    -0.50
    Tembelea
    -0.50
     meaning
    -0.50
     words
    -0.49
    ::$_
    -0.49
    RemoteException
    -0.47
     getCode
    -0.47
     StringTokenizer
    -0.46
    POSITIVE LOGITS
     propOrder
    0.70
    SourceChecksum
    0.56
     =",
    0.56
    ViewFeatures
    0.55
    webElementGuid
    0.52
    ⓧ
    0.51
    letoe
    0.51
    mixin
    0.51
    /−
    0.51
     &&
    0.50
    Activations Density 26.516%

    No Known Activations