© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    the boilerplate license text from the Apache 2.0 license and related terms

    oai_token-act-pair · gemini-2.0-flash

    Apache software license

    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
    Rhestr
    -0.78
    CloseOperation
    -0.73
    MENAFN
    -0.64
    PerformLayout
    -0.61
    Personendaten
    -0.61
    richTextPanel
    -0.59
    iastes
    -0.59
    granate
    -0.57
     onCreateView
    -0.56
    uxxxx
    -0.55
    POSITIVE LOGITS
    LElement
    0.50
    feri
    0.50
    !
    0.49
    әне
    0.49
    misi
    0.47
    CodedInputStream
    0.46
     Sp
    0.43
    ’)
    0.43
    essor
    0.43
    HttpClient
    0.43
    Activations Density 1.453%

    No Known Activations