© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12094
    Prev
    Next
    INDEX
    Explanations

    Latex and math markup.

    oai_token-act-pair · gemini-2.0-flash

    mathbb

    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
    Composable
    -0.52
     consultato
    -0.52
    ItemBackground
    -0.51
    Ecotoxicity
    -0.48
    ttemberg
    -0.48
    seteq
    -0.46
    AntiForgeryToken
    -0.45
     Fis
    -0.45
     che
    -0.45
     zug
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.69
    ^(@)
    0.60
     himſelf
    0.53
     onAnimation
    0.52
    ɚ
    0.52
     useRouter
    0.52
     băr
    0.51
     itſelf
    0.51
     Acción
    0.50
     cruzado
    0.50
    Activations Density 4.407%

    No Known Activations