© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5121
    Prev
    Next
    INDEX
    Explanations

    present tense verbs and participles, sometimes followed by "to".

    oai_token-act-pair · gemini-2.0-flash

    beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     transfieras
    -0.71
     autorytatywna
    -0.68
    rawDesc
    -0.65
    calientes
    -0.64
     iprot
    -0.63
    Portale
    -0.60
    anglès
    -0.60
     AssemblyTitle
    -0.60
    spesies
    -0.60
    MessageTagHelper
    -0.59
    POSITIVE LOGITS
    findpost
    0.58
    Xna
    0.51
    gorod
    0.51
     pat
    0.49
    icose
    0.49
     tuttavia
    0.48
    mopol
    0.48
    pat
    0.47
    czaj
    0.47
    entro
    0.46
    Activations Density 1.787%

    No Known Activations