© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for formatting math symbols and documents

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/coding

    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
    日閲覧
    -0.50
    Viel
    -0.44
     retroactive
    -0.44
    Portale
    -0.43
    发表于
    -0.43
    nowa
    -0.42
     بلکه
    -0.42
     AssemblyCulture
    -0.41
     Ses
    -0.41
     encoded
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.75
     Scalars
    0.58
     Bam
    0.56
    :✨
    0.55
     sliders
    0.54
    adera
    0.54
    +#+#
    0.54
     Dup
    0.53
    PullParser
    0.53
    kaper
    0.53
    Activations Density 0.694%

    No Known Activations