© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13691
    Prev
    Next
    INDEX
    Explanations

    the word "hero"

    oai_token-act-pair · gemini-2.0-flash

    hero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     '\\;'
    -1.21
     дописавши
    -0.90
     kasarigan
    -0.80
     <=",
    -0.79
    LookAnd
    -0.78
    sidemargin
    -0.74
    bootstrapcdn
    -0.73
    AccessorTable
    -0.73
    RectangleBorder
    -0.69
     newBuilder
    -0.68
    POSITIVE LOGITS
    ramienta
    0.56
    hicle
    0.52
    ώρα
    0.51
    ReadFile
    0.50
    Campe
    0.50
    }{*}{
    0.50
     œ
    0.50
    ssic
    0.50
    arao
    0.50
    FromFile
    0.49
    Activations Density 0.919%

    No Known Activations