© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3887
    Prev
    Next
    INDEX
    Explanations

    HTML code fragments

    oai_token-act-pair · gemini-2.0-flash

    HTML/XML tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    \}\\
    -0.84
     viewDidLoad
    -0.80
    "):
    -0.77
     Савезне
    -0.75
     CreateTagHelper
    -0.75
    ]<
    -0.74
    \{\\
    -0.71
    ameters
    -0.70
     Italijanski
    -0.69
     ".";
    -0.69
    POSITIVE LOGITS
    de
    0.48
    des
    0.44
    ra
    0.40
    re
    0.40
    n
    0.40
    Portail
    0.40
    N
    0.39
     letech
    0.38
    disc
    0.38
    0
    0.37
    Activations Density 0.839%

    No Known Activations