© 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. 5714
    Prev
    Next
    INDEX
    Explanations

    computer code and related terminology.

    oai_token-act-pair · gemini-2.0-flash

    Code and configurations

    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
     er
    -0.42
    hh
    -0.38
    ть
    -0.37
     me
    -0.37
     mere
    -0.36
     dem
    -0.35
     el
    -0.35
     pol
    -0.35
    ja
    -0.35
    ía
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.91
    DockStyle
    0.80
    исленность
    0.77
    complexContent
    0.73
    RegistryLite
    0.73
    Personendaten
    0.73
     betweenstory
    0.72
     Roskov
    0.71
     vägen
    0.71
    下载附件
    0.71
    Activations Density 5.461%

    No Known Activations