© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1504
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to law, legal issues, legal conclusions and intent, and judgement calls.

    oai_token-act-pair · gemini-2.0-flash

    problems, issues, mistakes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -0.69
    RegisterType
    -0.45
    ViewImports
    -0.45
    ніципалі
    -0.44
     gost
    -0.44
    RTHOOK
    -0.44
    aarrggbb
    -0.43
     purposes
    -0.42
    SharedCtor
    -0.42
     aimer
    -0.41
    POSITIVE LOGITS
    endphp
    0.76
    Tembelea
    0.75
    istoitu
    0.68
    jstor
    0.65
    ://"
    0.65
    cshtml
    0.63
     ioe
    0.62
     yyl
    0.59
     @"/
    0.59
    estic
    0.58
    Activations Density 28.984%

    No Known Activations