© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3351
    Prev
    Next
    INDEX
    Explanations

    text that appears to be French or a similar language, possibly in the context of an online chat.

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    bootstrapcdn
    -0.59
    WriteBarrier
    -0.59
    rrggbb
    -0.56
    MLLoader
    -0.53
    SequentialGroup
    -0.51
     mío
    -0.50
    istoitu
    -0.49
    httphttps
    -0.49
    horabuena
    -0.48
    nezeu
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.62
    bewerken
    0.59
    
    0.50
    mobileqq
    0.50
    autoconfigure
    0.49
    BindingResult
    0.48
     Chhat
    0.47
     NgModule
    0.47
    tificate
    0.46
    })$}
    0.45
    Activations Density 0.544%

    No Known Activations