© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5243
    Prev
    Next
    INDEX
    Explanations

    German language text.

    oai_token-act-pair · gemini-2.0-flash

    capitalized words or proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    istische

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Monfieur
    -1.57
     Efq
    -1.43
     purpoſe
    -1.38
     ſeveral
    -1.35
     pleaſure
    -1.34
     Majefty
    -1.31
     faſt
    -1.31
     Diſ
    -1.31
     reaſon
    -1.29
     Theſe
    -1.28
    POSITIVE LOGITS
     F
    0.46
     B
    0.45
     Ver
    0.42
     f
    0.41
     R
    0.41
     
    0.41
     mengen
    0.40
     ge
    0.39
     G
    0.38
     Post
    0.38
    Activations Density 8.132%

    No Known Activations