© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    various code snippets or documentation from different languages and formats

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     of
    -0.56
    ="@+
    -0.56
    <bos>
    -0.56
    en
    -0.53
    ,
    -0.52
    leetcode
    -0.51
    ModelAdmin
    -0.51
    อาด
    -0.50
     发表于
    -0.49
     or
    -0.48
    POSITIVE LOGITS
     propOrder
    0.83
    setVerticalGroup
    0.77
    rungsseite
    0.72
     مشين
    0.72
     useRouter
    0.68
    Toma
    0.66
    xase
    0.66
    StoryboardSegue
    0.66
    </tfoot>
    0.65
    Tembelea
    0.64
    Activations Density 1.837%

    No Known Activations