© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8671
    Prev
    Next
    INDEX
    Explanations

    what appear to be prefixes consisting of two or three letters

    oai_token-act-pair · gemini-2.0-flash

    computing code and paraffin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    に
    -0.89
    是
    -0.75
    mos
    -0.62
    ku
    -0.61
    ki
    -0.61
    了
    -0.57
    kor
    -0.55
    by
    -0.55
    kat
    -0.55
    ting
    -0.54
    POSITIVE LOGITS
     pageContext
    0.75
     myſelf
    0.62
    SharedCtor
    0.62
    #
    0.59
     CreateTagHelper
    0.57
    fjspx
    0.57
     vaut
    0.57
    npmjs
    0.57
     ويكيميديا
    0.57
     ISNI
    0.56
    Activations Density 1.098%

    No Known Activations