© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12926
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe other words

    oai_token-act-pair · gemini-2.0-flash

    word formation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     مشين
    -0.83
     propOrder
    -0.81
    ंदीखरीदारी
    -0.72
    Hozzáférés
    -0.69
    izziness
    -0.65
    ihnachten
    -0.65
     JpaRepository
    -0.64
     Efq
    -0.64
    锈钢
    -0.62
    KEYCODE
    -0.61
    POSITIVE LOGITS
    idental
    0.47
    後で
    0.47
     administrativos
    0.46
     üzerinde
    0.45
     avantage
    0.44
     possibilidades
    0.43
     directos
    0.43
     possibilité
    0.43
     Talvez
    0.43
     opérés
    0.42
    Activations Density 0.240%

    No Known Activations