© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11386
    Prev
    Next
    INDEX
    Explanations

    scientific text describing carbohydrates, sugar chains, links between sugars, and chemical composition

    oai_token-act-pair · gemini-2.0-flash

    Polysaccharides and monosaccharides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     تانيه
    -0.66
     vnode
    -0.66
     vectorstock
    -0.61
     >=",
    -0.61
    usermodel
    -0.60
    شهاد
    -0.59
    WebpackPlugin
    -0.59
     protoimpl
    -0.59
     Cavalier
    -0.59
     inevit
    -0.57
    POSITIVE LOGITS
    principalTable
    0.55
    zdro
    0.42
    gida
    0.41
    дации
    0.41
     Grace
    0.40
    มาะ
    0.40
     SwitchCompat
    0.39
    DriverManager
    0.39
    playSound
    0.39
     senior
    0.39
    Activations Density 1.486%

    No Known Activations