© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14238
    Prev
    Next
    INDEX
    Explanations

    the word "global" or "public" in code or text and sometimes the symbol "_"

    oai_token-act-pair · gemini-2.0-flash

    global

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     global
    -0.90
     Global
    -0.79
    global
    -0.71
    Global
    -0.69
     GLOBAL
    -0.66
     globally
    -0.65
    GLOBAL
    -0.63
     tqdm
    -0.63
     worldwide
    -0.59
    全球
    -0.58
    POSITIVE LOGITS
     viewType
    0.58
    发表于
    0.53
     puestos
    0.49
     automatiques
    0.48
    ://
    0.48
     présidenti
    0.48
    ::
    0.47
    OGND
    0.47
     pinulongan
    0.46
    +#+#
    0.45
    Activations Density 1.202%

    No Known Activations