© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9624
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming terms and Chinese characters

    oai_token-act-pair · gemini-2.0-flash

    words and phrases in Chinese and related characters

    np_token-act-pair-logits · gpt-4o-mini

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SourceChecksum
    -1.05
    Tikang
    -0.85
    Datuak
    -0.85
     Efq
    -0.81
    TagMode
    -0.81
     Jefus
    -0.76
     AssemblyCompany
    -0.75
     Shakspeare
    -0.74
    basicConfig
    -0.71
     pleaſure
    -0.71
    POSITIVE LOGITS
     of
    0.64
     them
    0.46
     का
    0.41
    之
    0.41
     konk
    0.40
     useHistory
    0.39
    ’
    0.39
    menistan
    0.39
     của
    0.37
    '
    0.34
    Activations Density 0.315%

    No Known Activations