© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2511
    Prev
    Next
    INDEX
    Explanations

    a combination of personal pronouns, auxiliary verbs, and the infinitive marker 'to'

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "to" and related phrases

    np_token-act-pair-logits · gpt-4o-mini
    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
     تضيفلها
    -0.65
    المكان
    -0.63
    Kontrola
    -0.59
    脚注の使い方
    -0.59
     Exacts
    -0.58
     AssemblyCulture
    -0.58
    ⓘ
    -0.51
    RUnlock
    -0.51
    MMV
    -0.50
    laway
    -0.49
    POSITIVE LOGITS
     Réponses
    0.62
     onCreate
    0.56
    IndentedString
    0.54
    чью
    0.52
    setVerticalGroup
    0.51
     getItemId
    0.50
    enoord
    0.49
     oprot
    0.46
     talk
    0.45
     ©️
    0.45
    Activations Density 1.467%

    No Known Activations