© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    mentions of publications with bibliographic information, often including dates and publishers

    oai_token-act-pair · gemini-2.0-flash

    Encyclopedia excerpts

    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
     protoimpl
    -0.66
     NgModule
    -0.65
     Roskov
    -0.59
    NgModule
    -0.59
    NewUrlParser
    -0.58
    ształ
    -0.53
    DCs
    -0.52
    Axial
    -0.52
    getline
    -0.50
    IsContent
    -0.50
    POSITIVE LOGITS
     дописавши
    0.56
    +#+#
    0.52
     doInBackground
    0.50
    ChildScrollView
    0.50
     kasarigan
    0.50
    iann
    0.47
     通販
    0.47
    isContained
    0.46
    AnchorTagHelper
    0.45
    SupportActionBar
    0.45
    Activations Density 1.055%

    No Known Activations