© 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. 9693
    Prev
    Next
    INDEX
    Explanations

    words related to computers and software, especially features and use

    oai_token-act-pair · gemini-2.0-flash

    prepositions/adverbs

    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
    CppCodeGen
    -0.78
    TagHelper
    -0.77
    ReusableCell
    -0.77
     Мексичка
    -0.70
     otomatig
    -0.68
    يكب
    -0.68
    SharedCtor
    -0.67
    findpost
    -0.67
     Wiktionnaire
    -0.66
    umenter
    -0.65
    POSITIVE LOGITS
     via
    0.65
     through
    0.63
     from
    0.60
     simply
    0.59
     simplemente
    0.49
     vanuit
    0.49
     easy
    0.48
     anywhere
    0.46
    simply
    0.44
     simplement
    0.44
    Activations Density 7.426%

    No Known Activations