© 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. 5349
    Prev
    Next
    INDEX
    Explanations

    the word "amid" and sometimes words ending in "d."

    oai_token-act-pair · gemini-2.0-flash

    conflict, crisis

    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
    DotNetBar
    -0.66
    исленность
    -0.61
     tqdm
    -0.59
    脚注の使い方
    -0.59
    +#+#
    -0.59
     الرياضيه
    -0.57
    esez
    -0.56
    tagHelper
    -0.54
    ytä
    -0.54
    ัฒนา
    -0.52
    POSITIVE LOGITS
    WebMethod
    0.74
    setContentView
    0.65
     morire
    0.63
     avoient
    0.62
     ég
    0.62
     feroit
    0.62
     ainfi
    0.62
     breasts
    0.62
     étoit
    0.61
    fillType
    0.60
    Activations Density 0.535%

    No Known Activations