© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14674
    Prev
    Next
    INDEX
    Explanations

    German language text, especially examples of complex verb constructions and modal verbs

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    ftagPool
    -0.69
    IndentedString
    -0.68
    UTERS
    -0.61
    Espèce
    -0.59
    Groetjes
    -0.58
    APORE
    -0.58
     Italijani
    -0.57
    ագրություններ
    -0.56
     Efq
    -0.55
    揄
    -0.54
    POSITIVE LOGITS
    ✷
    0.55
    Française
    0.49
     незавершена
    0.46
     nonatomic
    0.45
    wanted
    0.45
    lui
    0.45
     hann
    0.43
     Should
    0.42
    PRWEB
    0.42
     Wanted
    0.42
    Activations Density 0.085%

    No Known Activations