© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12364
    Prev
    Next
    INDEX
    Explanations

    text that seems to be in French

    oai_token-act-pair · gemini-2.0-flash

    French computer forum

    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
    AndroidJUnit
    -0.58
    IndentedString
    -0.54
    DOCTYPE
    -0.52
    OOC
    -0.52
     Gaulle
    -0.52
    Fordítás
    -0.52
    ($__
    -0.51
    prnewswire
    -0.51
    RESUMO
    -0.50
    δά
    -0.50
    POSITIVE LOGITS
     Dage
    0.59
    errHandler
    0.53
    دانشنامهٔ
    0.52
     Wagen
    0.50
    filepath
    0.50
    Activité
    0.50
    vician
    0.49
     للمعارف
    0.49
     مرئيه
    0.48
     odkazy
    0.48
    Activations Density 0.727%

    No Known Activations