© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11307
    Prev
    Next
    INDEX
    Explanations

    the verb "go" in its various forms

    oai_token-act-pair · gemini-2.0-flash

    come/go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    adaptiveStyles
    -0.81
     Roskov
    -0.77
    OrWhiteSpace
    -0.75
    etheless
    -0.73
     autorytatywna
    -0.73
     оригіналу
    -0.71
    enumi
    -0.71
    nestjs
    -0.71
     Parcelable
    -0.71
    FTFY
    -0.69
    POSITIVE LOGITS
    '
    0.51
    <bos>
    0.43
     spettacolo
    0.40
    मेल
    0.39
     råd
    0.39
     divertimento
    0.39
     kasarigan
    0.39
     attre
    0.39
     unha
    0.38
    FormTagHelper
    0.38
    Activations Density 0.111%

    No Known Activations