© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11571
    Prev
    Next
    INDEX
    Explanations

    likely russian words related to website development

    oai_token-act-pair · gemini-2.0-flash

    code and foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     م
    -0.54
     v
    -0.52
     S
    -0.52
     mar
    -0.51
     n
    -0.50
    S
    -0.49
     V
    -0.49
     dis
    -0.48
     س
    -0.48
     во
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.89
    AndEndTag
    0.88
    tanleria
    0.87
    MessageOf
    0.85
     مشين
    0.84
     snippetHide
    0.84
    WebVitals
    0.83
    itattu
    0.80
     '\\;'
    0.80
    دانشنامهٔ
    0.79
    Activations Density 0.359%

    No Known Activations