Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14347
    Prev
    Next
    INDEX
    Explanations

    various articles, prepositions, and adjectives.

    oai_token-act-pair · gemini-2.0-flash

    game

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     autorytatywna
    -0.55
     noDo
    -0.47
    >>>>>>>
    -0.42
     soát
    -0.42
    ше
    -0.42
    Hauptartikel
    -0.40
    NOPQRST
    -0.39
    IBUS
    -0.39
    ViewChild
    -0.38
     خارجية
    -0.38
    POSITIVE LOGITS
     game
    3.47
    game
    3.06
     GAME
    2.64
     Game
    2.59
    Game
    2.59
    GAME
    2.30
     games
    2.06
    ゲーム
    1.97
     juego
    1.93
     jogo
    1.91
    Activations Density 1.334%

    No Known Activations