© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    Java code syntax and keywords, particularly related to class and method declarations and variable scoping

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AccessorTable
    -0.88
     >=",
    -0.83
    ⓧ
    -0.78
    CodeAttribute
    -0.74
    ]=>
    -0.74
    <bos>
    -0.73
    DeleteBehavior
    -0.71
    Personensuche
    -0.69
     propOrder
    -0.69
    RetentionPolicy
    -0.68
    POSITIVE LOGITS
     ferons
    0.51
     ujednoznacz
    0.44
    tvguidetime
    0.43
    ?
    0.41
     unlike
    0.41
    .
    0.41
     rare
    0.40
     betyder
    0.40
    rare
    0.40
     odio
    0.39
    Activations Density 0.922%

    No Known Activations