© 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. 11609
    Prev
    Next
    INDEX
    Explanations

    source code commonalities

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    "):
    -0.80
     BoxFit
    -0.73
    "),
    -0.72
    "))
    -0.72
    __':
    -0.71
    __':
    -0.71
     EconPapers
    -0.70
    __":
    -0.69
     שוליים
    -0.69
    '):
    -0.69
    POSITIVE LOGITS
    出版年
    0.63
     Escribe
    0.52
     soir
    0.49
    waite
    0.48
     CHAPITRE
    0.47
    ebilir
    0.47
     Anſ
    0.47
     Añade
    0.43
     leek
    0.43
    füh
    0.42
    Activations Density 15.065%

    No Known Activations