© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12461
    Prev
    Next
    INDEX
    Explanations

    mentions of the university Université Paris-Saclay and email addresses

    oai_token-act-pair · gemini-2.0-flash

    French 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    原始内容存档于
    -0.63
    ⓘ
    -0.60
     tö
    -0.52
    _))
    -0.48
    atoire
    -0.48
     isLoading
    -0.48
    XMLSchema
    -0.48
     espectáculo
    -0.48
    WEBPACK
    -0.47
    原始内容
    -0.47
    POSITIVE LOGITS
     umgekehrt
    0.53
    UnsafeEnabled
    0.52
    ToMany
    0.52
    StructEnd
    0.51
     '\\;'
    0.50
     SIMBAD
    0.50
    pdev
    0.49
     blant
    0.49
     lakers
    0.47
    Diweddarwch
    0.47
    Activations Density 0.514%

    No Known Activations