© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns, especially "I", "we" and You"

    oai_token-act-pair · gemini-2.0-flash

    irregular or unique tokens

    np_token-act-pair-logits · gpt-4o-mini

    blog/forum posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Personensuche
    -0.70
    はじめに
    -0.64
    viewDidLoad
    -0.59
    AddTagHelper
    -0.59
     linkovi
    -0.59
     CGPoint
    -0.57
    TextWatcher
    -0.55
    PreferredItem
    -0.54
    __*/
    -0.54
    сылкі
    -0.54
    POSITIVE LOGITS
    nearly
    0.53
    ftagPool
    0.53
     chips
    0.49
     reck
    0.49
    piecze
    0.49
    Espèce
    0.49
    :✨
    0.47
    Française
    0.47
    ểm
    0.47
    Koordinaten
    0.47
    Activations Density 1.312%

    No Known Activations