© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12842
    Prev
    Next
    INDEX
    Explanations

    formal writing in patents and academic publications

    oai_token-act-pair · gemini-2.0-flash

    Non-English fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ThroughAttribute
    -0.48
     Forms
    -0.45
    非
    -0.44
     forms
    -0.44
    اج
    -0.43
     HasFactory
    -0.42
    aarrggbb
    -0.42
    <bos>
    -0.41
     Fon
    -0.41
    LLocation
    -0.41
    POSITIVE LOGITS
    nóstico
    0.71
    BeginContext
    0.69
    userdetails
    0.66
    addCriterion
    0.66
     Spisak
    0.65
    Manbalar
    0.65
    CodedInputStream
    0.64
    ipedi
    0.60
     Paglinawan
    0.60
    padek
    0.59
    Activations Density 0.600%

    No Known Activations