© 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. 12749
    Prev
    Next
    INDEX
    Explanations

    a wide range of punctuation and numbers, sometimes interspersed with words in seemingly random contexts

    oai_token-act-pair · 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
     Efq
    -0.03
     Monfieur
    0.01
    ^(@)
    0.05
     Theſe
    0.08
     themſelves
    0.08
    công
    0.12
     myſelf
    0.12
    ſelf
    0.12
     iconFacebook
    0.15
     becauſe
    0.16
    POSITIVE LOGITS
    MigrationBuilder
    1.13
    SpringBootTest
    1.07
     AssemblyCulture
    1.06
    SourceChecksum
    0.98
     للاسماء
    0.98
    +:+
    0.98
    bootstrapcdn
    0.97
    出版年
    0.97
    addContainerGap
    0.96
     estadounid
    0.96
    Activations Density 42.689%

    No Known Activations