© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6115
    Prev
    Next
    INDEX
    Explanations

    references to promotional material, figures and war

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Espèce
    -0.56
     sarili
    -0.50
     Opfer
    -0.47
     fadeIn
    -0.47
    limia
    -0.47
    SPATH
    -0.47
    SystemColors
    -0.47
    iprot
    -0.45
     Jehová
    -0.45
    HasIndex
    -0.45
    POSITIVE LOGITS
    bootstrapcdn
    0.71
    ">//
    0.65
    redd
    0.59
    ValueStyle
    0.59
     <=",
    0.57
    utnik
    0.54
     Auss
    0.54
     serangga
    0.53
     pageContext
    0.52
    chkin
    0.52
    Activations Density 0.523%

    No Known Activations