© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10404
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "would be"

    oai_token-act-pair · gemini-2.0-flash

    be

    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
    Diweddarwch
    -0.54
     avanti
    -0.54
    beforeEach
    -0.51
     للمعارف
    -0.50
    RUCT
    -0.49
    ows
    -0.48
    pravy
    -0.48
    BAR
    -0.48
    似的
    -0.47
     Quoi
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.60
    Abitanti
    0.52
    calaure
    0.51
     παρά
    0.50
     &___
    0.49
    HideFlags
    0.49
    ionario
    0.48
     MonoBehaviour
    0.47
    Tikang
    0.47
    Coordonnées
    0.47
    Activations Density 0.660%

    No Known Activations