© 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. 5285
    Prev
    Next
    INDEX
    Explanations

    German sentences, especially those discussing writing

    oai_token-act-pair · gemini-2.0-flash

    technical code-related terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     uſ
    -0.56
     uſed
    -0.55
     purpoſe
    -0.55
     poffe
    -0.55
     Porém
    -0.53
     poffible
    -0.51
    ukų
    -0.51
    portál
    -0.50
     Detalles
    -0.50
     Nadie
    -0.50
    POSITIVE LOGITS
    +#+#
    0.53
     viewDidLoad
    0.50
    wapV
    0.49
    wist
    0.47
     beginnetje
    0.47
    welijk
    0.47
     scaricare
    0.45
    ArrowToggle
    0.45
     strtok
    0.44
    <bos>
    0.43
    Activations Density 0.515%

    No Known Activations